INDEX

Explanations

unusual characters or symbols

oai_token-act-pair · gpt-3.5-turbo

occurrences of significant numerical values or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cuts

-0.66

rats

-0.62

tf

-0.57

manship

-0.56

ngth

-0.53

fired

-0.53

iton

-0.52

 Misc

-0.51

Fuk

-0.51

 Mechdragon

-0.50

POSITIVE LOGITS

ixture

0.70

Ì¶

0.66

combe

0.64

thinkable

0.63

ogh

0.63

 apologise

0.62

 councillor

0.60

acular

0.60

wil

0.59

abulary

0.58

Activations Density 0.070%

unusual characters or symbols

occurrences of significant numerical values or statistics

No Comments

No Known Activations