INDEX

Explanations

references to compatibility or suitability in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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



-0.72

parsedMessage

-0.62

 InputDecoration

-0.62

 ainfi

-0.60

 パンチラ

-0.60

 NSCoder

-0.59

<unused28>

-0.59

<unused23>

-0.59

[@BOS@]

-0.59

<unused14>

-0.59

POSITIVE LOGITS

 suit

0.83

 suited

0.76

 suits

0.69

 suitable

0.68

suit

0.65

Hel

0.57

suitable

0.57

suits

0.55

suited

0.54

 suitability

0.53

Activations Density 0.262%

references to compatibility or suitability in various contexts

No Comments

No Known Activations