INDEX

Explanations

variable assignments and function definitions in code

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

`_` followed by `id`

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 surla

-0.60

 nakalista

-0.55

 CreateTagHelper

-0.55

RegressionTest

-0.52

ContentAsync

-0.52

Ārējās

-0.51

saraba

-0.51

principalColumn

-0.51

rrggbb

-0.49

 للمعارف

-0.48

POSITIVE LOGITS

(_,

0.41

 Савезне

0.40

0.39

CppCodeGen

0.39

sil

0.38

 wasted

0.37

 referenties

0.36

 useless

0.36

useless

0.36

_,

0.36

Activations Density 0.004%

variable assignments and function definitions in code

`_` followed by `id`

No Comments

No Known Activations