INDEX

Explanations

references to the state of Idaho

oai_token-act-pair · gpt-3.5-turbo

references to the state of Idaho and its cities

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

Ü

-0.83

vous

-0.79

xual

-0.78

ullivan

-0.78

trigger

-0.75

thood

-0.75

icer

-0.72

edom

-0.71

hops

-0.70

 behav

-0.70

POSITIVE LOGITS

 Falls

1.27

 Idaho

1.00

 Springs

0.95

 Potato

0.94

 Rapids

0.86

keye

0.84

 Boise

0.81

 Oilers

0.78

Fas

0.78

sylvania

0.73

Activations Density 0.010%

references to the state of Idaho

references to the state of Idaho and its cities

No Comments

No Known Activations