INDEX

Explanations

references to mutual relationships and interactions between individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 leçons

-0.65

 Cline

-0.62

Kus

-0.61

 gouttes

-0.59

ίσ

-0.59

 dolayı

-0.58

']),

-0.57

 Plan

-0.56

Pry

-0.56

illou

-0.55

POSITIVE LOGITS

 AssemblyCulture

1.05

selves

0.99

 المعيارى

0.88

BeginContext

0.77

MOUTH

0.71

 nargin

0.71

argout

0.67

izer

0.66

thenReturn

0.66

feinander

0.65

Activations Density 0.059%

references to mutual relationships and interactions between individuals

No Comments

No Known Activations