INDEX

Explanations

the direction 'left' in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "left" in various contexts

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

alez

-0.77

 mathemat

-0.69

displayText

-0.69

issance

-0.69

alist

-0.69

MAT

-0.68

idated

-0.68

ITNESS

-0.68

REC

-0.68

NRS

-0.68

POSITIVE LOGITS

overs

1.12

wing

1.06

ward

0.89

hander

0.85

 wing

0.83

 handed

0.82

 hemisphere

0.81

 flank

0.78

 hand

0.77

wich

0.77

Activations Density 0.031%

the direction 'left' in various contexts

mentions of the word "left" in various contexts

No Comments

No Known Activations