INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

theless

-0.71

 Gift

-0.68

iggurat

-0.67

 Citadel

-0.67

[+]

-0.67

Ghost

-0.66

 Achievement

-0.64

rites

-0.64

uberty

-0.64

 Proxy

-0.64

POSITIVE LOGITS

lan

0.67

sers

0.65

vin

0.64

 manag

0.63

 Hond

0.62

nz

0.61

cru

0.61

llan

0.60

 rider

0.60

iewicz

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.