INDEX

Explanations

words related to stamps

oai_token-act-pair · gpt-3.5-turbo

references to postage stamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

izons

-0.88

SOURCE

-0.74

cffffcc

-0.74

ctory

-0.73

thodox

-0.73

 traged

-0.72

 Stras

-0.71

Kut

-0.70

ahime

-0.70

icter

-0.69

POSITIVE LOGITS

eding

1.05

 stamps

0.82

 stamp

0.81

ing

0.76

uation

0.76

itious

0.73

 goodbye

0.72

 duty

0.71

uity

0.71

arding

0.71

Activations Density 0.034%

words related to stamps

references to postage stamps

No Comments

No Known Activations