INDEX

Explanations

references to error codes and data formats in a technical context

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

Error codes or file IDs

np_acts-logits-general · gemini-2.0-flash

error codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

::_('

-0.64

Билгалдахарш

-0.60

djangoproject

-0.60

=$?

-0.59

 HttpNotFound

-0.57

encodeWith

-0.56

VersionUID

-0.55

UserScript

-0.55

]$}

-0.54

_));

-0.54

POSITIVE LOGITS

Vidite

0.78

 Assignee

0.65

 fjor

0.62

 externi

0.61

ConstraintMaker

0.60

HostException

0.60

rungsseite

0.60

astéroïdes

0.59

stays

0.59

 "..\..\

0.57

Activations Density 0.569%

references to error codes and data formats in a technical context

Error codes or file IDs

error codes

No Comments

No Known Activations