INDEX

Explanations

terms related to characterization or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

MessageTagHelper

-0.81

IBarButtonItem

-0.73

 שוליים

-0.71

COUVER

-0.70

ArrowToggle

-0.69

zzleHttp

-0.69

ężczy

-0.68

 citoy

-0.67

borderSide

-0.67

ingale

-0.67

POSITIVE LOGITS

ization

0.97

isation

0.77

istical

0.68

 traits

0.66

 characters

0.66

izations

0.65

istically

0.61

 Characters

0.59

 COUN

0.58

isti

0.56

Activations Density 0.071%

terms related to characterization or descriptions

No Comments

No Known Activations