INDEX

Explanations

the word "one" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "one."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

 Vaugh

-0.65

ãĥ©ãĥ³

-0.64

inently

-0.63

 earthqu

-0.63

 Ezek

-0.62

acements

-0.61

-0.60

lov

-0.59

ooks

-0.59

rollers

-0.59

POSITIVE LOGITS

elf

0.99

 hundred

0.97

 Hundred

0.95

 thousand

0.92

 sided

0.87

 Thousand

0.82

 dimensional

0.81

 person

0.78

auga

0.77

 handed

0.76

Activations Density 0.115%

the word "one" in various contexts

occurrences of the word "one."

No Comments

No Known Activations