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

+)

-0.67

 Salary

-0.61

 Decision

-0.60

 Bohem

-0.60

inav

-0.59

 contrace

-0.59

 Working

-0.59

 Sabb

-0.58

UE

-0.57

enstein

-0.56

POSITIVE LOGITS

ota

0.84

cific

0.76

unks

0.75

itzer

0.75

OTE

0.72

isations

0.68

achu

0.68

jriwal

0.67

oting

0.67

oters

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.