INDEX

Explanations

phrases related to classic things or concepts

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "classic" in relation to various cultural references and works

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

OTUS

-0.74

reen

-0.71

 Simulator

-0.71

earcher

-0.68

athering

-0.66

foreseen

-0.66

ttp

-0.66

lesh

-0.65

heed

-0.64

larg

-0.63

POSITIVE LOGITS

arily

0.98

isation

0.73

ised

0.72

marks

0.69

osaurs

0.69

 classics

0.69

 Revival

0.69

isable

0.69

icals

0.69

ocl

0.69

Activations Density 0.015%

phrases related to classic things or concepts

mentions of the term "classic" in relation to various cultural references and works

No Comments

No Known Activations