INDEX

Explanations

questions related to knowledge or information seeking

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

exitRule

-0.81

SourceChecksum

-0.73

 CreateTagHelper

-0.68

rawDesc

-0.62

DebuggerNonUser

-0.61

awtextra

-0.56

 CGRectMake

-0.55

stateMutability

-0.55

CGRectMake

-0.55

holds

-0.53

POSITIVE LOGITS

 recently

0.81

 yesterday

0.79

 ayer

0.75

 ontem

0.73

Yesterday

0.72

 Dicapai

0.72

 Yesterday

0.71

 недавно

0.70

 kürzlich

0.69

yesterday

0.69

Activations Density 0.282%

questions related to knowledge or information seeking

No Comments

No Known Activations