INDEX

Explanations

words related to software suites or groups of related tools

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

 Kast

-0.75

 McGovern

-0.75

 Drummond

-0.72

 Morgan

-0.71

 Brandenburg

-0.68

Morgan

-0.66

 Whitehead

-0.65

 Mele

-0.65

 mandatario

-0.65

 Edgar

-0.63

POSITIVE LOGITS

SU

1.15

Su

1.10

Su

1.09

Suk

1.05

Suits

1.04

 sucrose

1.02

 Sutherland

1.01

suits

0.98

 Suarez

0.97

 Suites

0.96

Activations Density 0.071%

words related to software suites or groups of related tools

No Comments

No Known Activations

words related to software suites or groups of related tools

No Comments

No Known Activations