INDEX

Explanations

references to franchises and their respective actors or elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

opend

-0.56

vyšší

-0.56

 nahilalakip

-0.53

----</

-0.52

릅

-0.52

发表于

-0.51

 Vign

-0.50

 castello

-0.50

 OMIT

-0.50

chutz

-0.50

POSITIVE LOGITS

</thead>

0.71

 franchise

0.69

 combineReducers

0.66

AccessorTable

0.63

SupportActionBar

0.63

franchise

0.61

 الحره

0.60

RenderAtEndOf

0.59

 noqa

0.59

addPreferredGap

0.58

Activations Density 2.058%

references to franchises and their respective actors or elements

No Comments

No Known Activations