INDEX

Explanations

numeric figures or percentages

oai_token-act-pair · gpt-3.5-turbo

phrases or expressions related to probability or likelihood

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

 enrichment

-0.76

 supervised

-0.62

 sever

-0.62

 resumed

-0.62

 contrace

-0.62

 turnover

-0.62

 inert

-0.62

 slic

-0.61

 sealing

-0.60

 deposits

-0.60

POSITIVE LOGITS

mares

0.85

undrum

0.79

 WATCHED

0.76

 clichÃ©

0.75

enna

0.73

icle

0.73

lance

0.72

ographical

0.70

doi

0.70

 cringe

0.69

Activations Density 1.578%

numeric figures or percentages

phrases or expressions related to probability or likelihood

No Comments

No Known Activations