INDEX

Explanations

phrases indicating affiliation, association, or belonging

oai_token-act-pair · gpt-3.5-turbo

references to specific organizations or entities linked to locations or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

Everything

-0.67

everything

-0.66

thank

-0.64

alore

-0.62

 reluctantly

-0.61

 eleg

-0.60

bra

-0.60

hooting

-0.59

onsense

-0.58

sie

-0.57

POSITIVE LOGITS

 either

1.04

or

1.02

any

0.96

 another

0.95

 ineligible

0.94

 specified

0.81

 certain

0.80

 other

0.79

imilar

0.77

 eligible

0.75

Activations Density 0.454%

phrases indicating affiliation, association, or belonging

references to specific organizations or entities linked to locations or contexts

No Comments

No Known Activations