INDEX

Explanations

HTML tags and elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.18.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

ScopeManager

-0.56

StoryboardSegue

-0.52

AccessorTable

-0.48

μως

-0.47

localctx

-0.45

pre

-0.45

 '\\;'

-0.44

def

-0.43

 angekommen

-0.43

 small

-0.43

POSITIVE LOGITS

SOUNDBITE

0.63

 sogni

0.54

 isKindOfClass

0.53

Gambas

0.53

ductors

0.52

ousands

0.52

 propTypes

0.52

ándolos

0.52

guien

0.51

 legais

0.51

Activations Density 0.022%

HTML tags and elements

No Comments

No Known Activations