INDEX

Explanations

mentions of influential figures/entities

oai_token-act-pair · gpt-3.5-turbo

references to influential individuals or entities

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

thia

-0.79

few

-0.76

©¶æ

-0.73

ft

-0.70

fter

-0.70

aked

-0.69

otide

-0.69

È

-0.69

VK

-0.69

gged

-0.69

POSITIVE LOGITS

 influential

0.94

 influ

0.90

 endorsements

0.90

 figures

0.82

 personalities

0.81

 influence

0.81

 role

0.79

 gossip

0.78

 endors

0.74

 pund

0.73

Activations Density 0.014%

mentions of influential figures/entities

references to influential individuals or entities

No Comments

No Known Activations