INDEX

Explanations

questions starting with "Why don't" or similar phrasings

oai_token-act-pair · gpt-3.5-turbo

negations or questions that challenge the status quo

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ORGE

-0.83

urst

-0.79

isers

-0.73

onyms

-0.71

soType

-0.71

EV

-0.70

arov

-0.70

ocene

-0.70

quickShipAvailable

-0.69

 Starts

-0.69

POSITIVE LOGITS

 properly

0.83

 adequately

0.81

 vacc

0.73

itia

0.69

 mention

0.67

icable

0.66

 reinvest

0.65

 assimil

0.65

 bother

0.65

 priorit

0.64

Activations Density 0.182%

questions starting with "Why don't" or similar phrasings

negations or questions that challenge the status quo

No Comments

No Known Activations