INDEX

Explanations

numerical comparisons and statistical results

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

findpost

-0.66

ProgressHUD

-0.61

étisme

-0.57

 MainAxisSize

-0.57

 Twenty

-0.55

 otomatig

-0.54

Twenty

-0.54

 Fifty

-0.53

 Sixty

-0.52

LLocation

-0.52

POSITIVE LOGITS

 three

2.31

 trio

2.09

three

2.07

 trois

1.87

Three

1.82

 Three

1.81

 THREE

1.74

 três

1.70

 drei

1.66

 drie

1.66

Activations Density 0.376%

numerical comparisons and statistical results

No Comments

No Known Activations