INDEX

Explanations

instances of the word "role."

oai_token-act-pair · gpt-3.5-turbo

references to acting roles in film and television

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

orld

-0.67

£ı

-0.66

 Bulg

-0.61

bidden

-0.60

undred

-0.59

collect

-0.58

False

-0.57

Oo

-0.57

 Rapt

-0.56

fty

-0.55

POSITIVE LOGITS

 roles

0.94

playing

0.94

 reversal

0.93

models

0.79

model

0.78

OTA

0.74

INAL

0.73

players

0.72

entials

0.72

played

0.72

Activations Density 0.025%

instances of the word "role."

references to acting roles in film and television

No Comments

No Known Activations