INDEX

Explanations

words related to a process of change or conversion

oai_token-act-pair · gpt-3.5-turbo

mentions of "transition" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

vern

-0.74

psc

-0.66

MN

-0.65

Wr

-0.62

olulu

-0.60

Eat

-0.60

ongs

-0.60

eq

-0.59

à¨

-0.59

asper

-0.59

POSITIVE LOGITS

 transitioning

1.06

 transition

0.95

 transitioned

0.92

ogue

0.91

 transitions

0.89

 Transition

0.83

figure

0.78

 phases

0.71

aroo

0.69

lus

0.69

Activations Density 0.018%

words related to a process of change or conversion

mentions of "transition" in various contexts

No Comments

No Known Activations