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

 digestion

-0.74

peat

-0.70

 bandwagon

-0.68

meat

-0.64

 machines

-0.62

 licenses

-0.62

 expansions

-0.61

 hiber

-0.60

ktop

-0.60

hare

-0.59

POSITIVE LOGITS

oshop

0.84

uran

0.74

ndra

0.74

izophren

0.69

Ì¶

0.69

erman

0.68

:=

0.68

oman

0.67

auder

0.67

isconsin

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.