INDEX

Explanations

references to blame and responsibility in political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

complexContent

-0.35

 beschik

-0.33

PREFERRED

-0.33

 módulos

-0.32

 yüksek

-0.31

 przec

-0.31

sbericht

-0.30

 Briefe

-0.30

Binding

-0.30

 umge

-0.30

POSITIVE LOGITS

 blame

1.13

blame

1.02

 blamed

0.90

 Blame

0.89

 blaming

0.82

Blame

0.82

 culpa

0.82

 blames

0.80

 guilty

0.71

 guilt

0.71

Activations Density 0.509%

references to blame and responsibility in political contexts

No Comments

No Known Activations