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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nai

-0.82

ucl

-0.77

owicz

-0.76

pta

-0.74

onte

-0.73

anski

-0.72

ajor

-0.72

ulty

-0.71

ari

-0.66

osi

-0.65

POSITIVE LOGITS

 Tomorrow

0.63

 Horses

0.62

 spons

0.61

ãĥ´ãĤ¡

0.61

 Machines

0.61

 unfolded

0.61

plugin

0.61

 Ahead

0.60

 engines

0.60

 ahead

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.