INDEX

Explanations

phrases containing the word "walk"

oai_token-act-pair · gpt-3.5-turbo

references to walking or walk-related activities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

milo

-0.80

cffff

-0.73

 circumst

-0.68

 competing

-0.68

ctic

-0.67

arial

-0.65

 pressures

-0.65

 serotonin

-0.64

xus

-0.64

 helium

-0.64

POSITIVE LOGITS

walk

1.20

walker

1.08

walking

1.00

Walk

0.96

own

0.92

ings

0.90

abouts

0.88

erness

0.87

bow

0.86

wright

0.85

Activations Density 0.012%

phrases containing the word "walk"

references to walking or walk-related activities

No Comments

No Known Activations