INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

reon

-0.82

Lear

-0.77

Pros

-0.77

pict

-0.70

>>>>>>>>

-0.70

pan

-0.69

yip

-0.68

Tri

-0.68

Sep

-0.68

sterdam

-0.66

POSITIVE LOGITS

ished

0.71

 herself

0.70

icist

0.67

 Borough

0.66

 Bridge

0.64

 Awakens

0.63

burgh

0.62

 himself

0.61

 shorth

0.59

 Sinclair

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.