INDEX

Explanations

occurrences of the substring "Ed" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

BASELINE

-0.72

 怎样

-0.62

checkable

-0.58

uginosa

-0.57

IBOutlet

-0.56

appy

-0.56

"))

-0.56

Gambas

-0.53

SourceType

-0.52

kret

-0.52

POSITIVE LOGITS

Ed

1.00

Ed

0.92

ed

0.88

ED

0.79

Eds

0.78

 Edmond

0.77

Edg

0.73

 kaarangay

0.71

 Edson

0.71

 edin

0.69

Activations Density 0.140%

occurrences of the substring "Ed" in various contexts

No Comments

No Known Activations

occurrences of the substring "Ed" in various contexts

No Comments

No Known Activations