INDEX

Explanations

requests for further information or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Roskov

-0.70

مصادر

-0.54

 springfox

-0.53

 vVar

-0.51

ranno

-0.50

SCS

-0.50

Transkript

-0.48

 fieldNum

-0.47

ImageField

-0.47

ondissement

-0.47

POSITIVE LOGITS

 HasFactory

0.57

 AssemblyTitle

0.57

stateProvider

0.56

awtextra

0.55

 createSlice

0.54

 fût

0.54

riam

0.54

UserScript

0.53

setVerticalGroup

0.53

 getragen

0.52

Activations Density 0.223%

requests for further information or examples

No Comments

No Known Activations