INDEX

Explanations

prefixes indicating closeness or approximation

oai_token-act-pair · gpt-3.5-turbo

phrases indicating near or significant threats or dangers

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

rul

-0.77

 Garland

-0.72

 Doodle

-0.69

 Cosmos

-0.68

 Cohn

-0.67

Zup

-0.66

 Rica

-0.66

 lesson

-0.65

 DRAG

-0.65

Ĥª

-0.65

POSITIVE LOGITS

sighted

1.08

earth

0.87

distance

0.85

const

0.84

sight

0.83

perfect

0.80

sil

0.80

equ

0.79

imp

0.78

future

0.77

Activations Density 0.035%

prefixes indicating closeness or approximation

phrases indicating near or significant threats or dangers

No Comments

No Known Activations