INDEX

Explanations

research-related terminologies and abbreviations associated with health and genetic conditions

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

coz

-0.80

UPI

-0.78

eto

-0.75

eman

-0.74

 Trem

-0.72

gdala

-0.70

 שוליים

-0.70

 Montagne

-0.70

 Sonnen

-0.69

 kare

-0.68

POSITIVE LOGITS

hhh

1.03

hhhh

1.00

hh

1.00

dh

0.99

fh

0.97

Rh

0.92

0.90

rh

0.90

ZH

0.90

DH

0.89

Activations Density 0.918%

research-related terminologies and abbreviations associated with health and genetic conditions

No Comments

No Known Activations