INDEX

Explanations

technical terms related to tech companies or products

oai_token-act-pair · gpt-3.5-turbo

terms related to social issues and scientific studies

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

ks

-0.84

lahoma

-0.74

utch

-0.73

phas

-0.73

rology

-0.72

ãĥĥ

-0.72

zig

-0.72

acity

-0.71

itone

-0.71

mere

-0.71

POSITIVE LOGITS

LY

1.58

ING

1.47

 EDITION

1.41

HEAD

1.41

OUS

1.41

OF

1.40

INGS

1.40

LINE

1.39

MAN

1.39

WOR

1.39

Activations Density 0.196%

technical terms related to tech companies or products

terms related to social issues and scientific studies

No Comments

No Known Activations