INDEX

Explanations

references to opting in or out of processes or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 nakalista

-1.03

ografija

-0.68

----</

-0.66

RegressionTest

-0.61

يكب

-0.58

 XCTest

-0.58

ANTLR

-0.55

brokes

-0.53

jwa

-0.52

 nahilalakip

-0.51

POSITIVE LOGITS

opt

1.10

 opting

1.07

 Term

1.00

 term

0.98

 opts

0.95

Term

0.93

 terms

0.92

 opted

0.90

Opt

0.90

TERM

0.89

Activations Density 0.204%

references to opting in or out of processes or services

No Comments

No Known Activations