INDEX

Explanations

references to articles or written pieces of content

oai_token-act-pair · gpt-3.5-turbo

references to articles

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

cffff

-0.87

cffffcc

-0.76

edient

-0.75

elsius

-0.74

pter

-0.74

cled

-0.70

bered

-0.69

 Nadu

-0.69

inav

-0.68

ascus

-0.66

POSITIVE LOGITS

meal

1.09

 articles

0.87

 article

0.79

 published

0.77

 titled

0.74

abal

0.73

 describing

0.73

 detailing

0.72

hook

0.72

RFC

0.69

Activations Density 0.026%

references to articles or written pieces of content

references to articles

No Comments

No Known Activations