INDEX

Explanations

words related to physical body parts, specifically the throat

oai_token-act-pair · gpt-3.5-turbo

references to the throat and related injuries or conditions

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

udeb

-0.76

atern

-0.66

CES

-0.65

 Athlet

-0.63

 Sigma

-0.62

 mete

-0.59

CAST

-0.58

Amazon

-0.58

notation

-0.56

 Woodward

-0.56

POSITIVE LOGITS

 throat

1.25

 throats

1.24

 slit

1.01

bone

0.96

pipe

0.95

ħĭ

0.91

 cavity

0.89

bones

0.86

piece

0.84

lines

0.81

Activations Density 0.007%

words related to physical body parts, specifically the throat

references to the throat and related injuries or conditions

No Comments

No Known Activations