INDEX

Explanations

evaluative comments about experiences, particularly in a dining or entertainment context

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

Positive reviews and sentiments

np_acts-logits-general · gemini-2.0-flash

positive sentiment and value

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

EndGlobalSection

-0.72

routeProvider

-0.70

脚注の使い方

-0.65

__':

-0.62

__":

-0.61

AddTagHelper

-0.59

ErrUnexpectedEOF

-0.58

ConstraintMaker

-0.58

UnsafeEnabled

-0.58

最快更新

-0.57

POSITIVE LOGITS

Very

0.60

Nice

0.58

👌

0.57

 👍

0.57

 Excellent

0.55

 matron

0.53

 Nice

0.53

 Very

0.53

👍

0.52

Excellent

0.52

Activations Density 0.031%

evaluative comments about experiences, particularly in a dining or entertainment context

Positive reviews and sentiments

positive sentiment and value

No Comments

No Known Activations