INDEX

Explanations

mentions of fighting or conflict

oai_token-act-pair · gpt-3.5-turbo

terms related to gliding or floating actions

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

hyde

-0.88

TAIN

-0.85

ÃįÃį

-0.76

cles

-0.76

ÄŁ

-0.76

DragonMagazine

-0.73

OLOGY

-0.72

ãĤŃ

-0.70

FINEST

-0.69

ITAL

-0.68

POSITIVE LOGITS

itz

1.11

amping

1.01

ib

0.99

itched

0.98

ashing

0.98

adiator

0.95

anz

0.94

immer

0.94

ancing

0.93

itter

0.93

Activations Density 0.006%

mentions of fighting or conflict

terms related to gliding or floating actions

No Comments

No Known Activations