INDEX

Explanations

terms related to embedding and identification processes

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

-0.56

 safe

-0.54

喜

-0.53

CR

-0.52

تال

-0.51

 vitro

-0.51

databind

-0.49

 desco

-0.49

 proced

-0.49

POSITIVE LOGITS

extAlignment

1.03

 تضيفلها

0.91

 كومونز

0.84

AxisAlignment

0.83

 doubtnut

0.82

 <>",

0.81

 ExecuteAsync

0.81

ScopeManager

0.79

FunctionFlags

0.78

ELTS

0.77

Activations Density 0.027%

terms related to embedding and identification processes

No Comments

No Known Activations