INDEX

Explanations

references to myths or misconceptions

oai_token-act-pair · gpt-3.5-turbo

references to myths and misconceptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

perature

-0.77

foreseen

-0.74

rared

-0.73

affer

-0.70

arnaev

-0.70

bern

-0.70

imentary

-0.69

emouth

-0.68

ktop

-0.68

Interstitial

-0.67

POSITIVE LOGITS

Myth

1.15

icist

1.08

 Myth

0.98

 myth

0.93

ril

0.92

olog

0.84

 myths

0.82

lore

0.81

ic

0.77

 Reincarn

0.75

Activations Density 0.016%

references to myths or misconceptions

references to myths and misconceptions

No Comments

No Known Activations