INDEX

Explanations

mentions of specific historical or biblical figures

oai_token-act-pair · gpt-3.5-turbo

references to historical or religious figures and texts

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

arial

-0.84

orie

-0.78

neau

-0.78

pick

-0.77

ifact

-0.77

rien

-0.76

rier

-0.76

ice

-0.73

arette

-0.73

aci

-0.71

POSITIVE LOGITS

theless

0.77

 Moses

0.77

frey

0.76

 Runes

0.74

heed

0.70

 Parish

0.67

 Rebirth

0.66

 Malone

0.66

ÄŁ

0.64

 mythology

0.64

Activations Density 0.036%

mentions of specific historical or biblical figures

references to historical or religious figures and texts

No Comments

No Known Activations