INDEX

Explanations

references to garages and garage-related activities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SourceChecksum

-0.79

AsUp

-0.76

 Forumite

-0.76

Бахар

-0.75

.*")]

-0.74

 AspNetCore

-0.73

wapV

-0.73

 ―――――

-0.73

 createSlice

-0.72

 חיצוניים

-0.71

POSITIVE LOGITS

 linguistique

0.61

govine

0.61

 kaip

0.59

[--

0.55

 Tenga

0.55

hspace

0.54

How

0.53

Runtime

0.53

 mukana

0.51

 lingü

0.51

Activations Density 0.136%

references to garages and garage-related activities

No Comments

No Known Activations