INDEX

Explanations

function definitions and callback structures in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Jefus

-1.11

 itſelf

-1.05

 Anſ

-1.04

 doubtnut

-1.04

 myſelf

-1.02

 ་་

-1.02

featureID

-1.01

 Monfieur

-1.00

 ModelExpression

-0.98

 houſe

-0.97

POSITIVE LOGITS

0.74

0.68

0.58

0.55

ch

0.53

ResponseWriter

0.52

0.48

us

0.47

0.46

Activations Density 0.027%

function definitions and callback structures in code

No Comments

No Known Activations