INDEX

Explanations

instances of the word "branded" or words related to branding

oai_token-act-pair · gpt-3.5-turbo

references to branding and brand-related content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ippi

-0.75

vati

-0.72

vous

-0.66

etheus

-0.64

Struct

-0.63

 compr

-0.63

pmwiki

-0.63

 Traps

-0.63

 Debor

-0.62

yip

-0.62

POSITIVE LOGITS

 branded

1.10

 branding

0.98

ovan

0.95

 loyalty

0.80

Brand

0.78

emark

0.76

iate

0.76

ging

0.74

branded

0.74

ovo

0.74

Activations Density 0.013%

instances of the word "branded" or words related to branding

references to branding and brand-related content

No Comments

No Known Activations