INDEX

Explanations

phrases related to knowledge, beliefs, and actions taken by individuals or groups

oai_token-act-pair · gpt-3.5-turbo

statements of knowledge or claims about various subjects

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

itaire

-0.59

eur

-0.55

earcher

-0.55

aml

-0.53

 advoc

-0.52

icter

-0.52

asus

-0.51

pex

-0.51

ogl

-0.50

Pass

-0.50

POSITIVE LOGITS

 themselves

1.12

selves

0.90

 selves

0.89

 THEIR

0.65

 their

0.64

MpServer

0.61

 helmets

0.61

 jointly

0.60

li

0.60

 asses

0.59

Activations Density 0.859%

phrases related to knowledge, beliefs, and actions taken by individuals or groups

statements of knowledge or claims about various subjects

No Comments

No Known Activations