INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 perspect

-0.74

 racks

-0.73

Afee

-0.72

 Canaver

-0.71

 Akin

-0.67

nets

-0.62

 stakes

-0.60

 dismant

-0.59

awa

-0.59

 sorts

-0.58

POSITIVE LOGITS

itudinal

0.81

vid

0.76

gin

0.72

pid

0.72

gary

0.68

appa

0.68

ibrary

0.66

gex

0.66

algia

0.64

hran

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.