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

irtual

-0.67

 Atkins

-0.66

aday

-0.65

ADRA

-0.65

ento

-0.65

transform

-0.64

illance

-0.64

osc

-0.63

 carbohyd

-0.62

earchers

-0.62

POSITIVE LOGITS

---------

0.70

jl

0.68

Prime

0.67

------

0.67

 Pieces

0.66

 Members

0.66

 PTSD

0.65

ilk

0.64

nai

0.63

Soc

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.