INDEX

Explanations

instances of motion or direction in relation to travel or progression

oai_token-act-pair · gpt-3.5-turbo

phrases indicating direction or movement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Mub

-0.77

uzz

-0.70

rehens

-0.70

Percent

-0.68

sylvania

-0.65

ressor

-0.64

hma

-0.62

 Corpus

-0.61

Mit

-0.60

 Strat

-0.60

POSITIVE LOGITS

heading

1.03

 heading

1.03

canon

0.87

pins

0.75

 adolesc

0.74

 toward

0.72

 Ahead

0.71

 towards

0.70

ãĤĭ

0.68

daq

0.68

Activations Density 0.006%

instances of motion or direction in relation to travel or progression

phrases indicating direction or movement

No Comments

No Known Activations