INDEX

Explanations

references to scoring or ratings in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 onCancelled

-0.74

AlterField

-0.72

 препратки

-0.72

=""/>

-0.70

 herum

-0.69

isnan

-0.69

zewod

-0.67

Gweler

-0.67

 hinein

-0.67

Hyde

-0.66

POSITIVE LOGITS

 scores

1.88

 score

1.79

 Scores

1.74

 scored

1.68

 Score

1.59

Scores

1.56

scores

1.54

 scoring

1.54

score

1.50

Score

1.47

Activations Density 0.039%

references to scoring or ratings in various contexts

No Comments

No Known Activations