INDEX

Explanations

words related to guarantees and reassurances

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

GenerationType

-0.83

****************

-0.74

aysia

-0.71

 Spicer

-0.71

полнитель

-0.69

newnode

-0.66

middot

-0.65

PLN

-0.65

taglia

-0.64

ことができました

-0.64

POSITIVE LOGITS

assure

1.28

 assure

1.21

 assures

1.17

 Assurance

1.16

Assurance

1.16

assured

1.16

assurance

1.15

 assuring

1.14

 assured

1.02

 themſelves

0.98

Activations Density 0.003%

words related to guarantees and reassurances

No Comments

No Known Activations