INDEX

Explanations

references to unisex bathrooms and related signage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

GraphicsUnit

-0.87

 ویکی‌پدیای

-0.68

'{@

-0.64

 Audiodateien

-0.61

 CreateTagHelper

-0.59

 mijne

-0.58

 “¿

-0.58

первых

-0.56

ագրություններ

-0.55

SuppressLint

-0.53

POSITIVE LOGITS

 vector

1.04

 Vector

0.95

 concept

0.90

 Concept

0.82

Vector

0.76

 вектор

0.75

Concept

0.73

vector

0.73

concept

0.71

 grunge

0.71

Activations Density 0.097%

references to unisex bathrooms and related signage

No Comments

No Known Activations