INDEX

Explanations

references to technology and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

skosten

-0.80

 chapters

-0.69

smöglichkeiten

-0.67

 ones

-0.67

 episodes

-0.66

 batches

-0.66

 operands

-0.65

gebras

-0.64

 portions

-0.64

stances

-0.64

POSITIVE LOGITS

 that

0.72

exitRule

0.59

 device

0.57

 system

0.57

 thats

0.56

 salariés

0.55

 regimen

0.55

 program

0.55

 scheme

0.54

 panel

0.54

Activations Density 1.750%

references to technology and related concepts

No Comments

No Known Activations