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

ibaba

-0.71

 Parenthood

-0.70

traumatic

-0.68

 curtains

-0.68

itars

-0.67

ilitating

-0.67

 Jagu

-0.66

inges

-0.66

abwe

-0.63

mares

-0.62

POSITIVE LOGITS

æĪ¦

0.84

CVE

0.67

rend

0.66

ween

0.65

[/

0.65

iaries

0.64

leg

0.63

 Siem

0.61

 Bloomberg

0.59

OURCE

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.