INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

liest

-0.72

farious

-0.72

omorphic

-0.71

 Objective

-0.71

 Ambro

-0.69

 Pengu

-0.69

borgh

-0.68

 è£ıè

-0.68

latable

-0.66

âĹ¼

-0.66

POSITIVE LOGITS

uria

0.69

 dinners

0.66

arel

0.62

 Fitzgerald

0.61

endi

0.60

vou

0.60

Das

0.60

 sweets

0.60

acca

0.60

 dictate

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.