INDEX

Explanations

references to personal mental states and self-management

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ConstraintMaker

-0.80

CppMethod

-0.66

 AssemblyCulture

-0.65

(!__

-0.59

GOTREF

-0.58

UnsafeEnabled

-0.57

 AppColors

-0.55

Gambas

-0.54

 CreateTagHelper

-0.53

IsContent

-0.52

POSITIVE LOGITS

 Insee

0.45

Frame

0.45

Abitanti

0.44

encodeWith

0.43

MessageTagHelper

0.43

 footing

0.42

blage

0.42

blon

0.42

 تقدم

0.41

var

0.41

Activations Density 0.216%

references to personal mental states and self-management

No Comments

No Known Activations