INDEX

Explanations

terms related to scoring and evaluation metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ""))

-0.61

 ""],

-0.59

isations

-0.58

SourceChecksum

-0.57

 ostavi

-0.57

 combineReducers

-0.56

expandindo

-0.55

}">

-0.54

 متعلقه

-0.54

 resourceCulture

-0.54

POSITIVE LOGITS

 Scores

1.00

 scores

0.94

card

0.92

scores

0.90

Scores

0.86

 CURIAM

0.82

 scored

0.74

cards

0.73

heet

0.71

 Scor

0.71

Activations Density 0.080%

terms related to scoring and evaluation metrics

No Comments

No Known Activations