INDEX

Explanations

terms related to publishing processes and editorial decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 AttributeSet

-0.51

su

-0.47

ru

-0.45

phylla

-0.45

 Roughly

-0.44

خ

-0.44

kmale

-0.44

 комби

-0.44

ske

-0.43

fu

-0.42

POSITIVE LOGITS

 BoxDecoration

0.93

 publisher

0.74

évaluateur

0.72

 تضيفلها

0.71

 Scopus

0.70

 journaux

0.70

publisher

0.69

 publishers

0.69

 reviewer

0.68

 referees

0.68

Activations Density 1.642%

terms related to publishing processes and editorial decisions

No Comments

No Known Activations