INDEX

Explanations

terms related to biological classification and gene regulatory functions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ButterKnife

-0.69

IntoConstraints

-0.54

достатки

-0.53

GraphicsUnit

-0.50

hoea

-0.47

 verantwort

-0.46

 vänt

-0.46

totalSupply

-0.45

ст

-0.45

 specchio

-0.44

POSITIVE LOGITS

 falls

1.96

 fall

1.95

 falling

1.59

fall

1.58

 FALL

1.47

Fall

1.47

 Fall

1.46

 Falling

1.46

falls

1.46

falling

1.44

Activations Density 1.008%

terms related to biological classification and gene regulatory functions

No Comments

No Known Activations