INDEX

Explanations

symbols and formatting used in programming or mathematical expressions

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

Code, tags, or technical terms

np_acts-logits-general · gemini-2.0-flash

word following "of"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

-0.89

-0.85

in

-0.84

con

-0.83

ha

-0.82

-0.81

pro

-0.80

vi

-0.80

POSITIVE LOGITS

Efq

1.90

 myſelf

1.78

 Jefus

1.77

 Houſe

1.73

 Monfieur

1.72

 itſelf

1.72

 himſelf

1.69

ſelf

1.69

 themſelves

1.67

 Anſ

1.64

Activations Density 0.548%

symbols and formatting used in programming or mathematical expressions

Code, tags, or technical terms

word following "of"

No Comments

No Known Activations