INDEX

Explanations

phrases indicating the presence of potential or possibility

oai_token-act-pair · gpt-3.5-turbo

references to potential, particularly in contexts suggesting capabilities or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

tein

-0.74

 Payton

-0.72

ĪĴ

-0.71

aten

-0.68

OTO

-0.68

phia

-0.68

cise

-0.68

 Engel

-0.67

cipline

-0.67

cloth

-0.66

POSITIVE LOGITS

ities

1.07

 pitfalls

0.95

ity

0.88

 adversaries

0.85

 usefulness

0.84

externalActionCode

0.82

ibilities

0.78

 hazards

0.78

atility

0.78

 payoff

0.77

Activations Density 0.045%

phrases indicating the presence of potential or possibility

references to potential, particularly in contexts suggesting capabilities or possibilities

No Comments

No Known Activations