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

een

-0.71

rh

-0.68

ieth

-0.67

enth

-0.66

phia

-0.66

fect

-0.66

asm

-0.65

EStream

-0.64

cases

-0.63

 Presents

-0.60

POSITIVE LOGITS

Catalog

0.75

organic

0.74

 ineffective

0.67

olate

0.66

elta

0.66

oga

0.65

atomic

0.64

iod

0.64

oca

0.64

efully

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.