INDEX

Explanations

specific identifiers or codes related to data structures or programming concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

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

-0.97

queryInterface

-0.93

 invokingState

-0.89

+#+#

-0.88

enderror

-0.88

MessageTagHelper

-0.87

ArgumentParser

-0.85

 referenties

-0.84

 initComponents

-0.84

LabelTagHelper

-0.84

POSITIVE LOGITS

hex

0.61

Hex

0.55

Hex

0.55

hex

0.55

 hexadecimal

0.53

parseColor

0.52

he

0.47

HEX

0.47

 hexagonal

0.46

adecimal

0.44

Activations Density 0.839%

specific identifiers or codes related to data structures or programming concepts

No Comments

No Known Activations