INDEX

Explanations

words related to capability or functionality

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

phazard

-0.43

ParseTree

-0.42

Tazama

-0.41

GTCX

-0.41

GenerationType

-0.40

 Савезне

-0.40

scribers

-0.40

wieś

-0.40

sendRedirect

-0.39

 incess

-0.39

POSITIVE LOGITS

able

1.99

 usable

1.97

izable

1.96

isable

1.89

ABLE

1.88

vable

1.85

 readable

1.84

 playable

1.84

usable

1.80

nable

1.79

Activations Density 1.891%

words related to capability or functionality

No Comments

No Known Activations

words related to capability or functionality

No Comments

No Known Activations