INDEX

Explanations

references to biological categories and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 '\\;'

-0.74

UrlResolution

-0.71

 propOrder

-0.60

 myſelf

-0.60

 noDo

-0.60

aarrggbb

-0.58

 okuyayım

-0.57

rrggbb

-0.56

 ſche

-0.54

Gambas

-0.54

POSITIVE LOGITS

 survey

0.49

 Survey

0.35

WhereInput

0.34

 respondents

0.32

 surveys

0.32

へ

0.31

 errors

0.31

versy

0.30

晨

0.30

styleable

0.30

Activations Density 1.550%

references to biological categories and classifications

No Comments

No Known Activations