INDEX

Explanations

words related to physical actions or objects that can be pushed

oai_token-act-pair · gpt-3.5-turbo

common suffixes or phonetic patterns in words

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Cummings

-0.66

OND

-0.62

 Grimes

-0.61

Introduced

-0.61

ALLY

-0.61

ATTLE

-0.61

 dispatch

-0.55

 Frequ

-0.54

 Duff

-0.54

schild

-0.53

POSITIVE LOGITS

ongyang

1.03

sylvania

0.96

merga

0.88

haps

0.87

umatic

0.84

Cola

0.83

adium

0.81

chedel

0.79

asant

0.79

sburgh

0.78

Activations Density 0.085%

words related to physical actions or objects that can be pushed

common suffixes or phonetic patterns in words

No Comments

No Known Activations