INDEX

Explanations

tokens related to structure or categories used in programming or data formats

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

HtmlAttribute

-0.56

gnore

-0.48

 doub

-0.48

 cellpadding

-0.47

/>

-0.47

 laminar

-0.46

 пан

-0.46

|}\

-0.45

ث

-0.44

endimiento

-0.44

POSITIVE LOGITS

 name

0.92

ID

0.85

 names

0.80

IDs

0.78

 UUID

0.75

的名字

0.74

ID

0.74

id

0.72

ids

0.72

UUID

0.71

Activations Density 0.467%

tokens related to structure or categories used in programming or data formats

No Comments

No Known Activations