INDEX

Explanations

names that appear to be of personal interest or importance

oai_token-act-pair · gpt-3.5-turbo

the presence of names or terms associated with individuals or entities (likely related to sports or entertainment)

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 faint

-0.61

 sarc

-0.60

 srfAttach

-0.59

 rusty

-0.59

ãĤª

-0.59

 constit

-0.59

atoes

-0.58

 foreseeable

-0.57

ourning

-0.57

 calories

-0.56

POSITIVE LOGITS

neys

0.96

dan

0.86

ernaut

0.82

eki

0.78

 Marriott

0.77

EStream

0.76

ansen

0.75

 Mehran

0.72

TAG

0.72

 Whedon

0.71

Activations Density 0.079%

names that appear to be of personal interest or importance

the presence of names or terms associated with individuals or entities (likely related to sports or entertainment)

No Comments

No Known Activations