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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 nonex

-0.85

umblr

-0.74

Original

-0.69

 marry

-0.68

 cradle

-0.67

 autos

-0.67

 anthrop

-0.67

Accessory

-0.65

Ma

-0.62

 marriage

-0.61

POSITIVE LOGITS

 Ceres

0.75

oval

0.73

luaj

0.72

strength

0.71

wcsstore

0.71

worthiness

0.69

pent

0.68

ments

0.68

ures

0.67

oug

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.