INDEX

Explanations

phrases indicating affiliation or association with organizations or entities

oai_token-act-pair · gpt-3.5-turbo

mentions of affiliations or associations with entities or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

aqu

-0.71

pter

-0.69

chat

-0.69

oufl

-0.64

Detailed

-0.64

pecting

-0.63

confidence

-0.63

bra

-0.62

pan

-0.62

=-=-=-=-=-=-=-=-

-0.61

POSITIVE LOGITS

 affili

1.15

 affiliated

1.15

hips

1.08

iliated

1.04

 affiliation

1.00

lia

0.93

 affiliate

0.88

affiliated

0.79

 affiliates

0.77

iance

0.76

Activations Density 0.014%

phrases indicating affiliation or association with organizations or entities

mentions of affiliations or associations with entities or groups

No Comments

No Known Activations