INDEX

Explanations

words related to geographical locations

oai_token-act-pair · gpt-3.5-turbo

terms related to counting or quantities

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

Else

-0.78

ABE

-0.70

 corp

-0.65

gging

-0.65

cap

-0.62

 Situation

-0.60

BIT

-0.60

 wolves

-0.59

Nusra

-0.59

nexus

-0.58

POSITIVE LOGITS

iful

1.34

enance

1.17

ifully

1.14

ount

1.05

eous

0.95

aine

0.94

ains

0.93

iers

0.91

icularly

0.89

ies

0.88

Activations Density 0.011%

words related to geographical locations

terms related to counting or quantities

No Comments

No Known Activations