INDEX

Explanations

English language filler words that add almost no meaning such as "they", "it", "could", "to", among others.

oai_token-act-pair · gemini-2.0-flash

variations of the word "ask"

np_token-act-pair-logits · gpt-4o-mini

asking

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.74

 MainAxisSize

-0.63

 nakalista

-0.60

 चीज़ों

-0.59

migrationBuilder

-0.59

 Мексичка

-0.57

 <<<<<<<<<<<<<<

-0.55

SourceChecksum

-0.52

twimg

-0.52

SBATCH

-0.51

POSITIVE LOGITS

ask

1.88

Ask

1.72

 asking

1.62

Ask

1.61

 asked

1.61

 asks

1.57

 request

1.54

ask

1.44

ASK

1.41

 Asking

1.39

Activations Density 2.418%

English language filler words that add almost no meaning such as "they", "it", "could", "to", among others.

variations of the word "ask"

asking

No Comments

No Known Activations