INDEX

Explanations

instances where the word "dozens" is mentioned

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "dozens."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ismo

-0.66

 hegemony

-0.64

abad

-0.63

Forge

-0.60

Dub

-0.59

igor

-0.59

MER

-0.59

Prim

-0.58

sole

-0.57

 Lover

-0.57

POSITIVE LOGITS

uously

0.89

 thousand

0.88

entimes

0.87

eenth

0.87

uous

0.79

 dozen

0.78

ourcing

0.77

paces

0.74

irtual

0.74

ensical

0.73

Activations Density 0.010%

instances where the word "dozens" is mentioned

occurrences of the word "dozens."

No Comments

No Known Activations