INDEX

Explanations

references to the color black

oai_token-act-pair · gpt-3.5-turbo

references to "black" in various contexts

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

PsyNetMessage

-0.90

=-=-=-=-

-0.85

ablishment

-0.85

 Lauder

-0.85

igslist

-0.84

ICLE

-0.83

OPLE

-0.82

mble

-0.78

xon

-0.77

 sidx

-0.73

POSITIVE LOGITS

smith

1.20

jack

1.06

ened

1.01

berry

1.01

moon

0.91

hawk

0.91

horse

0.90

bird

0.89

beard

0.86

powder

0.85

Activations Density 0.034%

references to the color black

references to "black" in various contexts

No Comments

No Known Activations