INDEX

Explanations

references to attributes related to data structures and their properties

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

Booleans and boolean-related terms

np_acts-logits-general · gemini-2.0-flash

boolean or whether

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

AccessorTable

-0.65

 CreateTagHelper

-0.61

makeConstraints

-0.56

psons

-0.55

Itoa

-0.51

nadequate

-0.50

ynthesis

-0.50

İM

-0.50

 endfor

-0.50

╚

-0.50

POSITIVE LOGITS

 boolean

2.01

bool

1.98

boolean

1.94

 bool

1.93

 whether

1.76

Boolean

1.73

 Boolean

1.70

BOOL

1.60

Bool

1.59

 Whether

1.52

Activations Density 0.449%

references to attributes related to data structures and their properties

Booleans and boolean-related terms

boolean or whether

No Comments

No Known Activations