INDEX

Explanations

terms related to indicators and dependencies in a variety of contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Beller

-0.70

 Doran

-0.69

PSA

-0.65

 Byron

-0.65

gerton

-0.65

 Mane

-0.64

 Council

-0.63

allery

-0.63

 Salt

-0.63

íritu

-0.62

POSITIVE LOGITS

IND

1.13

ind

1.13

Ind

1.11

ind

1.04

IND

1.03

 inds

1.01

Ind

1.00

AndEndTag

1.00

 Indes

0.97

NDR

0.95

Activations Density 0.561%

terms related to indicators and dependencies in a variety of contexts

No Comments

No Known Activations