INDEX

Explanations

quantitative measures or assessments related to degrees and intensity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

izop

-0.94

 سكانية

-0.81

 فريبيس

-0.76

Dum

-0.76

 gelassen

-0.75

 fout

-0.75

Dum

-0.75

 <>",

-0.75

Geplaatst

-0.75

 ['./

-0.74

POSITIVE LOGITS

 degrees

1.69

 Degrees

1.55

 degree

1.55

 Degree

1.47

Degree

1.39

degree

1.35

 DEGREE

1.34

degrees

1.34

Degrees

1.33

GREES

1.20

Activations Density 0.122%

quantitative measures or assessments related to degrees and intensity

No Comments

No Known Activations

quantitative measures or assessments related to degrees and intensity

No Comments

No Known Activations