INDEX

Explanations

words and phrases associated with fear, violence, and physical harm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 surla

-0.76

+#+

-0.61

Rüyada

-0.59

matchCondition

-0.58

AndEndTag

-0.57

 autorytatywna

-0.56

 AssemblyCulture

-0.56

 ligiloj

-0.55

=$?

-0.55

LabelTagHelper

-0.55

POSITIVE LOGITS

 beyond

1.07

 BEYOND

0.92

beyond

0.89

 senseless

0.89

 Beyond

0.85

Beyond

0.80

dry

0.76

 silly

0.75

 stiff

0.69

 habis

0.67

Activations Density 0.261%

words and phrases associated with fear, violence, and physical harm

No Comments

No Known Activations