INDEX

Explanations

words or phrases indicating types or categories of things

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

MigrationBuilder

-0.38

打

-0.34

いいのか

-0.34

KEYCODE

-0.34

ity

-0.34

 لينك

-0.34

⎞

-0.32

どうぞ

-0.32

ly

-0.32

สม

-0.32

POSITIVE LOGITS

dafx

0.71

 كومونز

0.66

ⓧ

0.62

InjectAttribute

0.59

OrNil

0.56

ruik

0.55

intios

0.55

makeText

0.54

uxxxx

0.54

istoitu

0.53

Activations Density 0.496%

words or phrases indicating types or categories of things

No Comments

No Known Activations