INDEX

Explanations

instances of the word "Let" and other words related to mathematical operations or hypothetical statements

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

 typelib

-0.65

URLException

-0.63

 onAnimation

-0.59

kloped

-0.57

telo

-0.57

Personensuche

-0.55

 transférez

-0.53

 onCancelled

-0.52

pad

-0.52

 استنادى

-0.52

POSITIVE LOGITS

 CreateTagHelper

0.81

 reaſon

0.69

 Jefus

0.69

 Chriftian

0.68

Efq

0.66

 ſtre

0.65

 espagne

0.62

 preſent

0.61

adecimal

0.61

 pleaf

0.61

Activations Density 0.050%

instances of the word "Let" and other words related to mathematical operations or hypothetical statements

No Comments

No Known Activations