INDEX

Explanations

prototyping terms and references in programming documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

:✨

-0.53

 florales

-0.52

 finnas

-0.52

 européennes

-0.50

 scelte

-0.50

 PLWABN

-0.48

国民

-0.48

<eos>

-0.48

 sentire

-0.48

 feront

-0.48

POSITIVE LOGITS

UrlResolution

0.95

bibinfo

0.75

PyExc

0.75

bibfield

0.74

$.

0.73

 myſelf

0.73

 itſelf

0.72

 themſelves

0.72

 Jefus

0.72

Efq

0.70

Activations Density 0.065%

prototyping terms and references in programming documentation

No Comments

No Known Activations