INDEX

Explanations

statistical terms and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

TintMode

-0.54

dafx

-0.47

 handle

-0.47

|}{$

-0.47

rava

-0.46

 idea

-0.45

UnifiedTopology

-0.45

ruptedException

-0.44

brainly

-0.43

POSITIVE LOGITS

 Table

1.11

Table

1.08

 Abbreviations

1.01

 table

0.96

Notes

0.92

Abbreviations

0.91

 Values

0.90

Note

0.89

 Note

0.88

Values

0.87

Activations Density 1.481%

statistical terms and medical conditions

No Comments

No Known Activations