INDEX

Explanations

medical and scientific references, particularly those detailing authorship and citation of papers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

 itſelf

-1.12

 Reſ

-1.07

 Conſ

-1.05

 themſelves

-1.02

 Anſ

-0.99

 Perſ

-0.98

 pleaſure

-0.98

 ſche

-0.97

 Diſ

-0.95

 Majefty

-0.93

POSITIVE LOGITS

et

0.52

*,

0.51

cstdio

0.47

__()

0.46

0.44

</strong>

0.43

.,

0.43

.;

0.43

0.42

PostConstruct

0.41

Activations Density 0.071%

medical and scientific references, particularly those detailing authorship and citation of papers

No Comments

No Known Activations