INDEX

Explanations

concepts related to comparisons and assessments of various topics

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

 Exactos

-0.63

 estimés

-0.63

MLLoader

-0.63

 AssemblyCulture

-0.60

GEBURTSDATUM

-0.59

("]");

-0.57

PyTuple

-0.56

⋱

-0.56

Xna

-0.54

 facie

-0.53

POSITIVE LOGITS

erman

0.50

 busy

0.50

uire

0.50

dorfer

0.49

 سبورت

0.48

ecture

0.47

ticism

0.47

fahrene

0.47

ividual

0.46

skosten

0.46

Activations Density 4.945%

concepts related to comparisons and assessments of various topics

No Comments

No Known Activations