INDEX

Explanations

variations of the word "wrap."

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "wrapping" or enclosing something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Lonely

-0.68

orie

-0.66

yton

-0.65

oi

-0.64

avanaugh

-0.64

relevant

-0.63

rade

-0.63

ugs

-0.62

hma

-0.62

localhost

-0.62

POSITIVE LOGITS

 wrap

1.04

wrap

0.97

 wrapped

0.93

 wrapping

0.92

 Wrap

0.92

 wraps

0.85

adoes

0.84

 shroud

0.81

neck

0.77

retch

0.76

Activations Density 0.029%

variations of the word "wrap."

terms related to the concept of "wrapping" or enclosing something

No Comments

No Known Activations