INDEX

Explanations

terms related to safety and risk factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

endpush

-0.56

PathVariable

-0.52

 dist

-0.50

tu

-0.49

#![

-0.49

Erreferentziak

-0.49

omla

-0.48

set

-0.47

 Seeder

-0.47

glBegin

-0.47

POSITIVE LOGITS

 issues

0.84

 soundness

0.75

 improvement

0.74

 adequacy

0.72

 issue

0.68

 Deter

0.68

issues

0.68

 shui

0.67

 assurance

0.66

improvement

0.65

Activations Density 1.024%

terms related to safety and risk factors

No Comments

No Known Activations