INDEX

Explanations

references to examples or illustrative cases

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

example variations

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

AccessorTable

-0.52

MessageTagHelper

-0.49

SourceChecksum

-0.49

zzleHttp

-0.44

PMailer

-0.44

balleur

-0.41

stdc

-0.40

TagMode

-0.40

localctx

-0.39

StackNavigator

-0.39

POSITIVE LOGITS

EXAMPLE

0.66

Example

0.65

exemple

0.58

 esimer

0.56

example

0.56

 esempi

0.54

 exemple

0.54

 example

0.53

 exemples

0.52

 exemplo

0.52

Activations Density 0.050%

references to examples or illustrative cases

example variations

No Comments

No Known Activations