INDEX

Explanations

words related to long-term timeframes and projections

oai_token-act-pair · gpt-3.5-turbo

phrases related to long-term considerations or impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hou

-0.79

IDES

-0.74

HOU

-0.74

 Cosponsors

-0.73

LET

-0.70

igers

-0.69

chy

-0.69

 Coul

-0.67

hs

-0.66

rote

-0.66

POSITIVE LOGITS

term

1.08

Term

0.89

ually

0.83

ptoms

0.75

etheless

0.74

ility

0.73

acy

0.73

 veter

0.72

 metic

0.72

cipled

0.72

Activations Density 0.011%

words related to long-term timeframes and projections

phrases related to long-term considerations or impacts

No Comments

No Known Activations