INDEX

Explanations

We are unable to accurately summarize the neuron's behavior as the provided activations do not contain consistent or distinguishing patterns

oai_token-act-pair · gpt-3.5-turbo

references to the name "Vic" and related terms

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

the name "Vic".

oai_token-act-pair · gemini-2.0-flash Triggered by @johnny

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

xual

-0.96

*/(

-0.85

Ô

-0.84

tenance

-0.77

SpaceEngineers

-0.75

landish

-0.75

mble

-0.72

paces

-0.71

 Flavoring

-0.68

yout

-0.68

POSITIVE LOGITS

arious

1.19

inity

1.01

abulary

0.98

isions

0.98

imated

0.95

imates

0.93

iple

0.93

entric

0.92

ente

0.92

uous

0.86

Activations Density 0.020%

We are unable to accurately summarize the neuron's behavior as the provided activations do not contain consistent or distinguishing patterns

references to the name "Vic" and related terms

the name "Vic".

No Comments

No Known Activations