INDEX

Explanations

code-related constructs and definitions for functions and conversions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

htë

-0.60

Portail

-0.60

 незавершена

-0.53

νή

-0.49

 चीज़ों

-0.49

 repetition

-0.48

athread

-0.48

 Repetition

-0.47

owieck

-0.47

 McClure

-0.47

POSITIVE LOGITS

 conversion

3.40

 convert

3.17

 Conversion

3.11

 converting

3.04

 converted

2.96

 conversions

2.94

 converts

2.87

 Convert

2.86

Conversion

2.85

conversion

2.84

Activations Density 0.583%

code-related constructs and definitions for functions and conversions

No Comments

No Known Activations