INDEX

Explanations

phrases related to statements or reports containing information or claims

oai_token-act-pair · gpt-3.5-turbo

references to reports or statements, often indicating what has been said or noted within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Maker

-0.68

Plex

-0.68

SAY

-0.65

grain

-0.65

ALE

-0.64

axe

-0.64

patch

-0.64

pron

-0.63

ãĥİ

-0.63

Pont

-0.63

POSITIVE LOGITS

 furthermore

0.75

 titled

0.75

 summar

0.74

seq

0.74

 quoting

0.73

 omin

0.73

 scathing

0.71

 secondly

0.69

 concise

0.68

 moreover

0.67

Activations Density 0.291%

phrases related to statements or reports containing information or claims

references to reports or statements, often indicating what has been said or noted within a document

No Comments

No Known Activations