INDEX

Explanations

examples provided are not sufficient to determine a specific pattern or preference for this neuron

oai_token-act-pair · gpt-3.5-turbo

the letter "g" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 sclerosis

-0.71

 derail

-0.69

 regist

-0.66

 moderator

-0.65

 Wonderful

-0.63

Rated

-0.63

 intern

-0.62

 booster

-0.61

 kickoff

-0.59

FINE

-0.59

POSITIVE LOGITS

asp

1.00

raphics

0.95

ardless

0.92

uild

0.84

ascript

0.83

bags

0.81

ars

0.79

athering

0.79

ods

0.78

oths

0.77

Activations Density 0.010%

examples provided are not sufficient to determine a specific pattern or preference for this neuron

the letter "g" in various contexts

No Comments

No Known Activations