INDEX

Explanations

relationships or correlations among various research findings

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

[Word] with/match/consistent/congruent [well/with]

np_acts-logits-general · gemini-2.0-flash

agreement and consistency

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

出版年

-0.68

 quæ

-0.56

 traction

-0.50

autoload

-0.46

حياته

-0.46



-0.45

 Fairbanks

-0.45

 fantasma

-0.45

std

-0.44

specifier

-0.43

POSITIVE LOGITS

 aligned

0.68

extAlignment

0.68

 aligns

0.66

+:+

0.62

ThroughAttribute

0.62

rolid

0.61

 BorderRadius

0.61

 suits

0.59

:+:

0.59

 AspNetCore

0.59

Activations Density 0.412%

relationships or correlations among various research findings

[Word] with/match/consistent/congruent [well/with]

agreement and consistency

No Comments

No Known Activations