INDEX

Explanations

phrases indicating expectations or predictions

oai_token-act-pair · gpt-3.5-turbo

terms related to expectations or what is presumed to happen

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

vertisement

-0.84

tein

-0.70

agra

-0.65

stein

-0.65

uel

-0.62

pmwiki

-0.61

 moot

-0.61

wick

-0.61

add

-0.60

wallet

-0.60

POSITIVE LOGITS

 greeted

0.69

 from

0.68

 Pascal

0.65

LY

0.65

 greets

0.65

oric

0.64

 given

0.63

antly

0.63

 awaited

0.63

OSH

0.63

Activations Density 0.067%

phrases indicating expectations or predictions

terms related to expectations or what is presumed to happen

No Comments

No Known Activations