INDEX

Explanations

phrases indicating a significant event or achievement in the past

oai_token-act-pair · gpt-3.5-turbo

references to historical significance or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouk

-0.80

affer

-0.78

illusion

-0.75

orney

-0.73

inki

-0.71

rien

-0.70

thening

-0.69

urances

-0.68

ym

-0.68

amina

-0.67

POSITIVE LOGITS

ISTORY

0.92

 history

0.87

era

0.77

 History

0.76

history

0.75

making

0.74

Era

0.70

 Corpus

0.69

arily

0.68

 record

0.68

Activations Density 0.018%

phrases indicating a significant event or achievement in the past

references to historical significance or events

No Comments

No Known Activations