INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ependent

-0.80

 Rover

-0.75

 relapse

-0.71

 regress

-0.67

ettel

-0.66

 regression

-0.62

ali

-0.62

 Canucks

-0.60

 brakes

-0.60

 inher

-0.59

POSITIVE LOGITS

hers

0.79

ignt

0.78

mask

0.70

Reply

0.70

hent

0.69

MN

0.69

eth

0.68

SUP

0.68

CHAR

0.67

uming

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.