INDEX

Explanations

concepts related to assumptions, violations, and the intricate dynamics between technology and secrets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

oredCriteria

-1.04

ThroughAttribute

-0.92

principalTable

-0.87

RegressionTest

-0.86

DockStyle

-0.85

 propOrder

-0.85

хьтан

-0.84

RepeatedField

-0.83

 كومونز

-0.82

setVerticalGroup

-0.82

POSITIVE LOGITS

 every

0.48

 everywhere

0.47

 some

0.45

 EVERY

0.44

 jeder

0.44

 elke

0.43

 irgende

0.43

 SOME

0.43

secrets

0.43

 alltid

0.43

Activations Density 0.384%

concepts related to assumptions, violations, and the intricate dynamics between technology and secrets

No Comments

No Known Activations