INDEX

Explanations

function definitions and calls related to setting parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

ſelf

-0.79

 Darum

-0.79

 fread

-0.79

 Stande

-0.78

 NDEBUG

-0.77

 оригіналу

-0.77

 ARXIV

-0.77

OfBirth

-0.76

 itſelf

-0.76

ftance

-0.76

POSITIVE LOGITS

set

1.28

SET

1.26

set

1.22

Set

1.21

Set

1.10

SET

1.07

 Sets

1.04

 Seton

0.97

 sets

0.97

sets

0.96

Activations Density 0.054%

function definitions and calls related to setting parameters

No Comments

No Known Activations