INDEX

Explanations

mentions of a specific brand or product named "Go" with different variations in the text

oai_token-act-pair · gpt-3.5-turbo

references to "Go" related products, brands, or franchises

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

creen

-0.90

ipation

-0.69

ament

-0.69

 ceilings

-0.68

uctor

-0.65

terday

-0.65

ussen

-0.63

itionally

-0.63

 leveled

-0.63

 plaus

-0.61

POSITIVE LOGITS

lems

1.09

verning

1.04

Daddy

0.95

ogly

0.95

ogl

0.92

etz

0.89

vt

0.89

ethe

0.84

og

0.80

vier

0.78

Activations Density 0.035%

mentions of a specific brand or product named "Go" with different variations in the text

references to "Go" related products, brands, or franchises

No Comments

No Known Activations