INDEX

Explanations

the name "Brittan"

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual, presumably "Lord Britt."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

hook

-0.85

-0.83

isSpecialOrderable

-0.79

Dub

-0.69

tenance

-0.68

reprene

-0.67

ptive

-0.66

font

-0.66

mouth

-0.65

sf

-0.64

POSITIVE LOGITS

ohyd

0.81

 GOODMAN

0.76

ALLY

0.75

 mund

0.69

nect

0.68

ITION

0.68

inders

0.68

 Cosponsors

0.67

 Britt

0.66

perse

0.65

Activations Density 0.044%

the name "Brittan"

references to a specific individual, presumably "Lord Britt."

No Comments

No Known Activations