INDEX

Explanations

references to forceful actions or coercion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 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

NOPQRST

-0.86

 Venedig

-0.85

richTextPanel

-0.82

roidered

-0.82

ươi

-0.80

خواندن

-0.79

 Marav

-0.77

 Pilgrims

-0.77

derry

-0.76

thmetic

-0.76

POSITIVE LOGITS

 Force

1.43

 force

1.39

 FORCE

1.33

 Forces

1.32

force

1.32

Force

1.32

FORCE

1.31

 forces

1.21

forces

1.13

Forces

1.10

Activations Density 0.078%

references to forceful actions or coercion

No Comments

No Known Activations