INDEX

Explanations

references to semesters and artificial constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

@"/

-0.85

 препратки

-0.82

{{$

-0.79

 оригіналу

-0.77

\{\\

-0.77

$/,

-0.76

}}">

-0.75

}</

-0.74

Vos

-0.74

 المعيارى

-0.74

POSITIVE LOGITS

 semester

1.11

Sem

0.97

 SEMESTER

0.97

SEM

0.97

 Semester

0.95

semester

0.91

 članak

0.89

Sem

0.88

SEM

0.88

sem

0.80

Activations Density 0.068%

references to semesters and artificial constructs

No Comments

No Known Activations