INDEX

Explanations

ages in the form of decades (e.g., 20s, 30s)

oai_token-act-pair · gpt-3.5-turbo

references to age groups or generational categories

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

ãģĵ

-0.66

OVER

-0.65

Reviewer

-0.64

Grab

-0.64

Sund

-0.62

 snipp

-0.62

Unity

-0.61

Ĩ

-0.61

ISON

-0.61

ãĤ¡

-0.60

POSITIVE LOGITS

omet

0.89

idia

0.85

atell

0.85

olutions

0.82

ources

0.82

ixties

0.80

leeve

0.80

idency

0.76

omething

0.76

atisf

0.76

Activations Density 0.038%

ages in the form of decades (e.g., 20s, 30s)

references to age groups or generational categories

No Comments

No Known Activations