INDEX

Explanations

terms related to leaks and bodily fluids

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArgsConstructor

-0.58

 templ

-0.51

IsMutable

-0.50

ROLS

-0.49

mány

-0.49

 Normdatei

-0.48

 vulné

-0.46

ngdoc

-0.46

 StatelessWidget

-0.46

ldt

-0.45

POSITIVE LOGITS

 leakage

0.93

 leaking

0.93

 emission

0.87

 leaks

0.85

leak

0.85

 leaked

0.85

 leak

0.84

Leak

0.82

 Leaks

0.79

 emitted

0.79

Activations Density 0.437%

terms related to leaks and bodily fluids

No Comments

No Known Activations