INDEX

Explanations

references to victims in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

isNotBlank

-0.38

稽

-0.37

nodoc

-0.36

 variances

-0.35

WriteLiteral

-0.35

*}

-0.35

 terras

-0.35

-0.34

 Morm

-0.34

 Audiodateien

-0.34

POSITIVE LOGITS

 victim

2.39

 victims

2.20

victim

2.14

 Victim

2.08

Victim

2.03

 Victims

1.92

 victime

1.82

 victimes

1.77

 vítima

1.74

 víctima

1.70

Activations Density 0.251%

references to victims in various contexts

No Comments

No Known Activations