INDEX

Explanations

references to functions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 erwartet

-0.40

malige

-0.39

daje

-0.37

 Mejía

-0.37

Overlay

-0.36

 teuer

-0.35

 leichte

-0.35

 earliest

-0.35

cached

-0.34

 glaubt

-0.34

POSITIVE LOGITS

 Function

1.29

function

1.20

 function

1.18

Function

1.17

 Functions

1.12

 Func

1.08

 FUNCTION

1.08

FunctionType

1.06

 functions

1.05

FUNCTION

1.05

Activations Density 0.141%

references to functions in programming contexts

No Comments

No Known Activations