INDEX

Explanations

references to various issues and problems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sponges

-0.89

 otomatig

-0.78

politan

-0.76

mew

-0.75

\}\\

-0.73

 Pires

-0.73

 Rebekah

-0.72

Maf

-0.71

 sogni

-0.71

 Meli

-0.71

POSITIVE LOGITS

 issues

1.48

 Issues

1.44

Issues

1.43

issues

1.41

 ISSUES

1.36

 issue

1.28

ISSUES

1.26

 ISSUE

1.24

ISSUE

1.22

Issue

1.22

Activations Density 0.080%

references to various issues and problems

No Comments

No Known Activations