INDEX

Explanations

the concept of familiarity or recognition in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<unused52>

-0.94

<unused28>

-0.94

<unused21>

-0.94

<unused68>

-0.94

[@BOS@]

-0.94

<unused41>

-0.93

<unused74>

-0.93

<unused14>

-0.93

<pad>

-0.93

<unused3>

-0.93

POSITIVE LOGITS

 familiar

0.54

<bos>

0.52

0.40

Familiar

0.35

’

0.33

familiar

0.32

 Familiar

0.31

 featured

0.30

 familiarity

0.30

trás

0.30

Activations Density 0.498%

the concept of familiarity or recognition in various contexts

No Comments

No Known Activations