INDEX

Explanations

phrases indicating quality or effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 AssemblyCulture

-0.77

<eos>

-0.66

IndentedString

-0.61

 mosquitoes

-0.61

ⓧ

-0.60

uxxxx

-0.59

 referenties

-0.59

parsedMessage

-0.59

 affidavit

-0.56

ClientSize

-0.54

POSITIVE LOGITS

\{\\

0.74

BibitemShut

0.72

lillah

0.69

$_"

0.69

ghijklmnop

0.68

"):

0.67

LEncoder

0.65

 specific

0.65

şekkür

0.65

NUMX

0.65

Activations Density 0.506%

phrases indicating quality or effectiveness

No Comments

No Known Activations