INDEX

Explanations

references to toxicity levels and dosages in studies involving substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/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.13.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

円

-0.54

shadowColor

-0.46

perasi

-0.46

jera

-0.46

 daqui

-0.44

 Архивировано

-0.43

mpro

-0.43

romic

-0.42

cplusplus

-0.42

aktery

-0.42

POSITIVE LOGITS

 doses

0.77

 concentrations

0.74

 dose

0.73

 Theſe

0.71

 myſelf

0.71

dose

0.70

 itſelf

0.70

 Shakspeare

0.69

 quantités

0.69

Efq

0.69

Activations Density 1.267%

references to toxicity levels and dosages in studies involving substances

No Comments

No Known Activations