INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

REDACTED

-0.82

pedia

-0.67

CLASSIFIED

-0.63

Matrix

-0.62

-0.60

PO

-0.60

GU

-0.59

NEWS

-0.58

FML

-0.58

GRE

-0.58

POSITIVE LOGITS

eton

0.84

olesterol

0.76

ucked

0.74

esity

0.71

fur

0.70

ottest

0.70

rows

0.69

laus

0.68

aft

0.68

nutrition

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.