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

pc

-0.98

ortium

-0.79

heed

-0.72

geon

-0.70

amic

-0.70

iac

-0.70

 crumble

-0.68

-0.64

cale

-0.64

fman

-0.64

POSITIVE LOGITS

GGGGGGGG

0.81

inventoryQuantity

0.80

BUS

0.75

ategory

0.66

generated

0.59

IDENT

0.57

 prints

0.57

VD

0.57

OAD

0.56

IME

0.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.