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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

soDeliveryDate

-0.82

REDACTED

-0.74

URA

-0.71

ACTED

-0.71

ADRA

-0.69

âĶĢâĶĢ

-0.69

é¾

-0.67

ä

-0.67

LAT

-0.66

Nap

-0.64

POSITIVE LOGITS

hurst

0.69

ific

0.69

widget

0.68

walker

0.67

stroke

0.67

nets

0.67

ibur

0.67

uan

0.66

 Marketplace

0.62

ector

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.