INDEX

Explanations

programming-related keywords or functions

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

-0.58

OrUpdate

-0.52

onOptions

-0.50

-0.49

us

-0.49

癮

-0.49

-0.48

im

-0.48

-0.47

POSITIVE LOGITS

CodeAnalysis

3.34

 myſelf

1.16

 itſelf

1.09

 himſelf

1.02

 poffible

0.97

ſelves

0.96

Scénario

0.95

 raiſ

0.95

neſs

0.94

ſelf

0.93

Activations Density 0.000%

programming-related keywords or functions

No Comments

No Known Activations