INDEX

Explanations

terms related to toxicity and dosage levels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 recevrez

-0.44

nson

-0.43

<bos>

-0.42

पया

-0.42

-0.41

 aufges

-0.41

 possesso

-0.41

 nepř

-0.41

ownic

-0.41

Ge

-0.40

POSITIVE LOGITS

 مرئيه

0.69

Eventually

0.68

NUMX

0.67

eventually

0.67

BeginContext

0.66

ReusableCell

0.66

ultimate

0.66

Ultimately

0.65

 kasarigan

0.65

 outright

0.65

Activations Density 0.730%

terms related to toxicity and dosage levels

No Comments

No Known Activations