INDEX

Explanations

occurrences of logos and their relation to branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 autorytatywna

-0.60

op

-0.59

dom

-0.58

scriptcase

-0.56

 createSlice

-0.55

kaŭ

-0.55

-0.54

///<

-0.53

𝘃

-0.53

POSITIVE LOGITS

 logos

2.00

 logo

1.98

 Logo

1.89

 LOGO

1.89

logo

1.86

Logo

1.78

logos

1.70

 Logos

1.66

LOGO

1.61

 лого

1.47

Activations Density 0.070%

occurrences of logos and their relation to branding

No Comments

No Known Activations