INDEX

Explanations

terms related to significant events, actions, or developments

oai_token-act-pair · gpt-3.5-turbo

phrases expressing concern or raising alarms about significant issues

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

 goddamn

-0.80

ividual

-0.77

 fucking

-0.73

 godd

-0.70

!!!!!!!!

-0.69

acion

-0.66

 marvelous

-0.65

 negro

-0.65

 damn

-0.65

 Proper

-0.64

POSITIVE LOGITS

 Kremlin

0.81

 crackdown

0.79

Reuters

0.78

 shortages

0.77

 lawmaker

0.76

 Reuters

0.73

 analysts

0.73

glers

0.72

 contentious

0.70

Critics

0.70

Activations Density 0.568%

terms related to significant events, actions, or developments

phrases expressing concern or raising alarms about significant issues

No Comments

No Known Activations