INDEX

Explanations

terms related to activation and performing specific actions

oai_token-act-pair · gpt-3.5-turbo

terms related to activation processes and states

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

esan

-0.78

 Abram

-0.70

birth

-0.66

apest

-0.66

yah

-0.65

 Norman

-0.64

ago

-0.63

 Apost

-0.63

elf

-0.62

orf

-0.61

POSITIVE LOGITS

activated

0.89

 activation

0.88

 charcoal

0.82

activation

0.79

uates

0.78

 activated

0.76

uated

0.73

 activate

0.72

 activating

0.71

 suppression

0.71

Activations Density 0.042%

terms related to activation and performing specific actions

terms related to activation processes and states

No Comments

No Known Activations