INDEX

Explanations

words related to specific interests or hobbies, particularly involving technology or community gatherings

oai_token-act-pair · gpt-3.5-turbo

references to various groups of enthusiasts across different interests

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

tein

-0.71

ãĥĥãĥī

-0.68

 Pesh

-0.64

 Walls

-0.64

downs

-0.62

Khe

-0.60

outs

-0.59

emb

-0.59

lining

-0.59

met

-0.59

POSITIVE LOGITS

 hobby

0.89

ORPG

0.80

 enthusiasts

0.79

sonian

0.78

ateurs

0.77

rpm

0.77

ateur

0.77

 flock

0.77

£ı

0.74

 enthusiast

0.71

Activations Density 0.019%

words related to specific interests or hobbies, particularly involving technology or community gatherings

references to various groups of enthusiasts across different interests

No Comments

No Known Activations