INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

Pay

-0.80

pay

-0.75

 Guys

-0.73

rieved

-0.69

 Drew

-0.68

 paying

-0.66

 funn

-0.64

 pays

-0.64

Buk

-0.61

story

-0.61

POSITIVE LOGITS

yip

0.98

pse

0.84

á½

0.82

ItemTracker

0.77

netflix

0.75

fleet

0.74

imaru

0.71

ascript

0.70

cill

0.70

ktop

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.