INDEX

Explanations

terms related to activation processes and activities

oai_token-act-pair · gpt-3.5-turbo

words related to activism and active engagement in social issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

esan

-0.69

lli

-0.64

drivers

-0.64

oglu

-0.64

yah

-0.64

lihood

-0.61

Lay

-0.59

fare

-0.59

forward

-0.59

lings

-0.58

POSITIVE LOGITS

activated

0.85

 charcoal

0.83

aline

0.78

ãĤ¿

0.76

nect

0.74

ãĤ¯

0.73

aze

0.72

ISTER

0.72

uated

0.72

ãĤ±

0.71

Activations Density 0.070%

terms related to activation processes and activities

words related to activism and active engagement in social issues

No Comments

No Known Activations