INDEX

Explanations

names and proper nouns, particularly those associated with places and characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

 "..\..\

-0.73

ThroughAttribute

-0.70

featureID

-0.70

UserScript

-0.70

bitField

-0.69

aarrggbb

-0.68

twimg

-0.67

 createSlice

-0.65

exprimer

-0.63

 "..\..\..\

-0.62

POSITIVE LOGITS

存于互联网档案馆

0.67

 Majefty

0.52

Skocz

0.49

Duk

0.47

setFirstName

0.47

\]

0.47

 Voyager

0.47

\_(

0.46

Oak

0.46

 Philist

0.45

Activations Density 0.287%

names and proper nouns, particularly those associated with places and characters

No Comments

No Known Activations