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

TAG

-0.79

TYPE

-0.75

 Ended

-0.72

 Classes

-0.71

OTH

-0.69

inged

-0.69

ET

-0.67

Fans

-0.67

VERTISEMENT

-0.67

OT

-0.65

POSITIVE LOGITS

rero

0.74

yon

0.72

psons

0.70

uten

0.69

rity

0.68

pul

0.65

iona

0.63

idates

0.63

Peb

0.63

figured

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.