INDEX

Explanations

verbs "is", "are", and forms of "be" combined with nouns associated with political or medical documents.

oai_token-act-pair · gemini-2.0-flash

attacks

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-0.69

 виправивши

-0.67

LayoutConstraint

-0.66

PerformLayout

-0.64

ViewImports

-0.62

 تضيفلها

-0.60

Pranala

-0.58

CreateModel

-0.57

 attracted

-0.56

AccessorTable

-0.55

POSITIVE LOGITS

hit

1.17

 targeted

1.01

 attacked

0.85

 affected

0.84

 visited

0.83

 penetrated

0.80

 reached

0.79

 invaded

0.79

 struck

0.78

 approached

0.78

Activations Density 7.604%

verbs "is", "are", and forms of "be" combined with nouns associated with political or medical documents.

attacks

No Comments

No Known Activations