INDEX

Explanations

phrases containing the word "one" followed by an adjective

oai_token-act-pair · gpt-3.5-turbo

the word "one" 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 @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ooks

-0.70

ourn

-0.64

gif

-0.63

cats

-0.63

older

-0.62

hips

-0.62

ories

-0.58

ãĤ¢

-0.57

ãĤ¬

-0.57

NZ

-0.56

POSITIVE LOGITS

 hundred

0.94

 Hundred

0.83

 sided

0.79

 embodiment

0.79

 wonders

0.78

 thousand

0.77

 thing

0.74

 dimensional

0.74

 crore

0.66

esan

0.66

Activations Density 0.122%

phrases containing the word "one" followed by an adjective

the word "one" in various contexts

No Comments

No Known Activations