INDEX

Explanations

instances of the word "myth" or related words

oai_token-act-pair · gpt-3.5-turbo

mentions of "myth" or related terms

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

perature

-0.76

Interstitial

-0.74

foreseen

-0.71

orneys

-0.70

arnaev

-0.67

baugh

-0.66

hani

-0.66

artney

-0.66

ktop

-0.65

ecause

-0.65

POSITIVE LOGITS

icist

1.17

Myth

1.11

ril

0.97

 Myth

0.96

olog

0.93

ological

0.85

ologies

0.84

 myth

0.84

lore

0.80

busters

0.80

Activations Density 0.019%

instances of the word "myth" or related words

mentions of "myth" or related terms

No Comments

No Known Activations