INDEX

Explanations

sources or references in a text

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate the presence of unspecified sources or references in statements

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

ĸļ

-0.87

osate

-0.80

aeper

-0.71

eer

-0.67

arrow

-0.67

eers

-0.66

emale

-0.65

ecake

-0.64

 pend

-0.64

avorite

-0.64

POSITIVE LOGITS

 sources

0.98

 informants

0.86

 Sources

0.80

 source

0.78

source

0.75

 consulted

0.73

 briefed

0.73

 informant

0.72

alyst

0.72

 priv

0.71

Activations Density 0.017%

sources or references in a text

phrases that indicate the presence of unspecified sources or references in statements

No Comments

No Known Activations