INDEX

Explanations

references to taste and tasting experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sesta

-0.60

-0.59

 capitolo

-0.54

<b>

-0.52

<h2>

-0.52

ț

-0.51

 infierno

-0.51

 yere

-0.51

uğ

-0.50

Explanation

-0.50

POSITIVE LOGITS

^(@)

0.92

 resourceCulture

0.91

]")]

0.89

tvguidetime

0.89

 AssemblyCulture

0.86

StoryboardSegue

0.83

AnchorStyles

0.82

 Mode

0.81

THEOREM

0.80

 taste

0.79

Activations Density 0.133%

references to taste and tasting experiences

No Comments

No Known Activations