INDEX

Explanations

code snippets that define variables and functions, particularly in programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

SequentialGroup

-0.95

ⓧ

-0.83

 CreateTagHelper

-0.78

GraphicsUnit

-0.77

__(/*!

-0.76

 שוליים

-0.75

 estimés

-0.75

 חיצוניים

-0.72

ScopeManager

-0.72

ειτουργ

-0.69

POSITIVE LOGITS

éndole

0.47

 rechange

0.45

PlainText

0.43

 rayo

0.43

raz

0.43

 circon

0.43

 Already

0.43

nières

0.43

 quarante

0.43

ocusing

0.42

Activations Density 0.538%

code snippets that define variables and functions, particularly in programming languages

No Comments

No Known Activations