INDEX

Explanations

sentences that provide positive evaluations or feedback

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Text followed by question/answer format

np_acts-logits-general · gemini-2.0-flash

guide me

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AppCompatTheme

-0.60

født

-0.54

("

-0.51

Rejo

-0.51

ennom

-0.51

randomUUID

-0.50

<--

-0.50

often

-0.48

gheny

-0.48

 arguably

-0.48

POSITIVE LOGITS

InjectAttribute

0.61

<eos>

0.61

")));

0.58

 rescheduled

0.58

=$?

0.57

basicConfig

0.56

rima

0.56

 jätte

0.55

expandindo

0.55

 staff

0.54

Activations Density 0.026%

sentences that provide positive evaluations or feedback

Text followed by question/answer format

guide me

No Comments

No Known Activations