INDEX

Explanations

leaders, politicians, and government-related terms

oai_token-act-pair · gpt-3.5-turbo

references to notable companies, figures, and political events

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

Els

-0.79

é¾įå

-0.72

$.

-0.72

Translation

-0.71

Ò

-0.70

}.

-0.70

Sov

-0.69

ãĥ¼ãĥĨ

-0.68

ãģĻ

-0.67

ãĤ¯

-0.64

POSITIVE LOGITS

 reacted

0.92

 announced

0.89

 awoke

0.86

 unveiled

0.86

 welcomes

0.85

 reacts

0.82

has

0.81

 celebrates

0.81

 apologized

0.81

 responded

0.79

Activations Density 0.613%

leaders, politicians, and government-related terms

references to notable companies, figures, and political events

No Comments

No Known Activations