INDEX

Explanations

names and references to individuals and their associations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Southwark

-0.76

westen

-0.74

ēc

-0.74

 Stande

-0.73

 Cardinals

-0.71

 sympy

-0.71

CARD

-0.71

 Cards

-0.71

meanor

-0.70

Gön

-0.69

POSITIVE LOGITS

apache

0.76

 Bradley

0.71

tabular

0.70

 defaultstate

0.69

 "','

0.69

fork

0.69

orithmic

0.68

 ascer

0.68

Bradley

0.67

Skor

0.67

Activations Density 2.360%

names and references to individuals and their associations

No Comments

No Known Activations