INDEX

Explanations

the word "stand" or related variations in a context suggesting support, unity, or opposition

oai_token-act-pair · gpt-3.5-turbo

instances of the word "stand" and its variations

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

ilers

-0.75

nesota

-0.72

iling

-0.70

illian

-0.69

ilic

-0.69

esters

-0.69

metry

-0.64

phrine

-0.63

olesc

-0.63

iler

-0.63

POSITIVE LOGITS

still

1.20

 tall

0.83

 upright

0.72

 steadfast

0.71

enance

0.71

 desks

0.71

up

0.70

 vigil

0.69

up

0.69

 taller

0.69

Activations Density 0.024%

the word "stand" or related variations in a context suggesting support, unity, or opposition

instances of the word "stand" and its variations

No Comments

No Known Activations