INDEX

Explanations

punctuation marks and authorship references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 désolés

-0.66

astify

-0.64

Bronnen

-0.58

errHandler

-0.58

ResumeLayout

-0.57

 Jefus

-0.56

 contd

-0.56

XmlIgnore

-0.55

elemField

-0.55

UBLIC

-0.55

POSITIVE LOGITS

springframework

0.99

spring

0.53

Sp

0.48

 spring

0.47

 spending

0.47

 Spring

0.46

 EconPapers

0.44

gians

0.43

RenderAtEndOf

0.42

Spring

0.41

Activations Density 0.034%

punctuation marks and authorship references

No Comments

No Known Activations