INDEX

Explanations

mentions of sheep

oai_token-act-pair · gpt-3.5-turbo

references to sheep and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

SPONSORED

-0.79

 disadvant

-0.79

 fortun

-0.75

 contrace

-0.75

ENTS

-0.74

Cooldown

-0.72

 validity

-0.72

ATIONS

-0.68

 unlaw

-0.68

 nostalg

-0.67

POSITIVE LOGITS

ishly

1.11

dogs

1.09

dog

1.07

skin

1.05

poke

0.85

ish

0.84

bats

0.83

bow

0.81

kies

0.80

MQ

0.79

Activations Density 0.034%

mentions of sheep

references to sheep and related terms

No Comments

No Known Activations