INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

words associated with arguments or debates

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

staking

-0.75

 corrid

-0.61

 attribution

-0.56

DEV

-0.56

 patched

-0.55

 mainline

-0.55

 mosaic

-0.55

 pandemonium

-0.54

 ashore

-0.54

 disinfect

-0.54

POSITIVE LOGITS

iy

0.95

ai

0.92

iri

0.87

icz

0.87

angan

0.85

oro

0.84

oy

0.84

iaz

0.84

ua

0.83

aru

0.83

Activations Density 0.310%

proper nouns or names

words associated with arguments or debates

No Comments

No Known Activations