INDEX

Explanations

verb phrases indicating a display or demonstration of something

oai_token-act-pair · gpt-3.5-turbo

phrases related to the absence of feelings or signs

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

 Noel

-0.75

adish

-0.65

 Sweeney

-0.63

 Conrad

-0.62

 venture

-0.62

 Debor

-0.61

 Vaughan

-0.61

 Stewart

-0.59

 sugg

-0.59

 Ambrose

-0.59

POSITIVE LOGITS

actly

0.79

natureconservancy

0.77

flame

0.76

png

0.71

redd

0.70

formance

0.70

hematically

0.68

matically

0.68

 resemblance

0.67

inline

0.67

Activations Density 0.227%

verb phrases indicating a display or demonstration of something

phrases related to the absence of feelings or signs

No Comments

No Known Activations