INDEX

Explanations

numeric values and codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ंदीखरीदारी

-0.84

PerformLayout

-0.84

-0.81

ttino

-0.78

 ModelExpression

-0.76

Parcelize

-0.76

RegressionTest

-0.75

UnusedPrivate

-0.72

parsedMessage

-0.71

IntoConstraints

-0.71

POSITIVE LOGITS

lisle

0.58

avía

0.48

 jedis

0.46

ys

0.45

Sys

0.44

,:);

0.44

יש

0.43

 body

0.42

//

0.42

TSD

0.42

Activations Density 0.221%

numeric values and codes

No Comments

No Known Activations