INDEX

Explanations

instances of the word "force" and its variations relating to coercion or compulsion

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IBarButtonItem

-0.86

 giapp

-0.85

 nakalista

-0.85

@[+][

-0.84

 étoient

-0.83

 anún

-0.82

 &___

-0.82

 AssemblyCompany

-0.82

roidered

-0.81

LEncoder

-0.81

POSITIVE LOGITS

 forced

0.91

Forced

0.90

 Forced

0.88

0.68

0.65

 forcing

0.65

forced

0.59

 glass

0.58

yu

0.58

 Kase

0.58

Activations Density 0.015%

instances of the word "force" and its variations relating to coercion or compulsion

No Comments

No Known Activations