INDEX

Explanations

positive evaluations and descriptors of various forms of media

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/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.15.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

uxxxx

-0.68

PyExc

-0.58

eBook

-0.58

CURLOPT

-0.56

thylene

-0.55

Occurrences

-0.55

 xlink

-0.54

 CURLOPT

-0.52

urlopen

-0.52

andere

-0.52

POSITIVE LOGITS

 outstanding

0.86

 excellent

0.86

 superb

0.83

excellent

0.80

 quality

0.73

outstanding

0.73

 terrific

0.72

 worthy

0.70

 excellence

0.69

quality

0.68

Activations Density 0.228%

positive evaluations and descriptors of various forms of media

No Comments

No Known Activations