INDEX

Explanations

terms related to tax-related discussions or analyses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

 CEST

-0.36

 INTERESAR

-0.35

 Wachs

-0.35

iteľ

-0.35

TokenNameRBRACE

-0.35

BCC

-0.35

WebElementEntity

-0.34

athione

-0.34

outSlope

-0.34

níky

-0.34

POSITIVE LOGITS

DV

1.24

GV

1.22

PV

1.20

FV

1.19

RV

1.19

HV

1.17

BV

1.16

LV

1.15

DV

1.14

KV

1.11

Activations Density 1.235%

terms related to tax-related discussions or analyses

No Comments

No Known Activations