INDEX

Explanations

repetitive patterns or structures in text, particularly where formatting or specific code structures are used

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

Code snippets with "return"

np_acts-logits-general · gemini-2.0-flash

return and programming constructs

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-1.03

-1.02

-0.99

-0.97

-0.96

POSITIVE LOGITS

 myſelf

1.89

 itſelf

1.84

 pleaſure

1.71

 greateſt

1.59

 themſelves

1.58

 purpoſe

1.58

 reaſon

1.58

 ſmall

1.57

ſelves

1.56

 ſeveral

1.56

Activations Density 0.741%

repetitive patterns or structures in text, particularly where formatting or specific code structures are used

Code snippets with "return"

return and programming constructs

No Comments

No Known Activations