INDEX

Explanations

key-value pairs typically seen in JSON or API request/response formats

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

was applied

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

HomeAsUpEnabled

-0.52

findpost

-0.40

anglicky

-0.40

 PeEnEo

-0.39

InjectAttribute

-0.39

 насељу

-0.36

 ContentValues

-0.36

 estekak

-0.36

StoryboardSegue

-0.32

 whose

-0.30

POSITIVE LOGITS

tagHelperRunner

0.68

 pleaſure

0.65

ftagPool

0.65

 autorytatywna

0.64

ロウィン

0.61

 defaultstate

0.61

 tartalomajánló

0.59

AddTagHelper

0.58

linawan

0.57



0.56

Activations Density 0.010%

key-value pairs typically seen in JSON or API request/response formats

was applied

No Comments

No Known Activations