INDEX

Explanations

references to actions or processes related to evaluation and decision-making

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 applau

-0.58

enumii

-0.56

 виправивши

-0.56

InputTagHelper

-0.54

 fuis

-0.54

<!--[

-0.53

 inoxydable

-0.51

 sánchez

-0.51

 Innoc

-0.51

ientras

-0.50

POSITIVE LOGITS

que

0.95

Que

0.75

Que

0.73

QUE

0.72

expandindo

0.68

 quien

0.65

providedIn

0.64

matchCondition

0.64

 què

0.62

que

0.61

Activations Density 0.170%

references to actions or processes related to evaluation and decision-making

No Comments

No Known Activations