INDEX

Explanations

relationships and references in scientific or technical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 purpoſe

-1.11

 Monfieur

-1.09

 ſeveral

-1.05

 myſelf

-1.02

 leaſt

-1.01

 preſent

-1.00

 Inſ

-1.00

 faſt

-1.00

 Reſ

-0.97

 ſtate

-0.97

POSITIVE LOGITS

0.54

0.53

0.52

ias

0.51

Activations Density 0.058%

relationships and references in scientific or technical data

No Comments

No Known Activations

relationships and references in scientific or technical data

No Comments

No Known Activations