INDEX

Explanations

references to different phases within processes or experiments

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

!*\

-0.54

gister

-0.53

ecg

-0.48

tut

-0.48

stdc

-0.47

import

-0.45

 CreateTagHelper

-0.45

 للاسماء

-0.43

 bind

-0.42

 Unto

-0.42

POSITIVE LOGITS

Ph

0.82

Ph

0.82

 Phan

0.76

PH

0.76

Phase

0.75

ph

0.73

PH

0.71

Phi

0.71

 Phase

0.71

Phi

0.70

Activations Density 0.413%

references to different phases within processes or experiments

No Comments

No Known Activations