INDEX

Explanations

mentions of significant events or incidents

oai_token-act-pair · gpt-3.5-turbo

occurrences of significant events and claims made in news reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Newsletter

-0.79

-0.77

iations

-0.65

velt

-0.62

GG

-0.60

whatever

-0.58

VD

-0.57

è¦ļéĨĴ

-0.57

omatic

-0.56

mentioned

-0.56

POSITIVE LOGITS

 watchdog

0.73

 Belfast

0.71

 whistleblower

0.62

 archaeologists

0.62

 honoured

0.60

 Bihar

0.60

NZ

0.60

 Kerala

0.60

 embattled

0.59

 Nasa

0.58

Activations Density 1.110%

mentions of significant events or incidents

occurrences of significant events and claims made in news reports

No Comments

No Known Activations