INDEX

Explanations

statements expressing gratitude or requests for assistance

oai_token-act-pair · gpt-3.5-turbo

expressions of desire or preference

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

VERTISEMENT

-0.84

ingen

-0.72

@#&

-0.70

sequence

-0.69

shock

-0.65

aan

-0.63

idious

-0.62

ubb

-0.62

aring

-0.61

 Jung

-0.61

POSITIVE LOGITS

 revenge

0.74

 forgiveness

0.70

 ransom

0.68

 assurances

0.66

 clarification

0.63

 assurance

0.62

 redress

0.62

gery

0.62

hya

0.61

lier

0.61

Activations Density 0.042%

statements expressing gratitude or requests for assistance

expressions of desire or preference

No Comments

No Known Activations