INDEX

Explanations

references to the name "Stan" followed by varying numbers

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of the name "Stan."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

Îµ

-0.76

 leve

-0.73

 ãĥ

-0.71

NX

-0.69

Î³

-0.69

 Ascend

-0.69

aligned

-0.67

alis

-0.67

aid

-0.66

´

-0.66

POSITIVE LOGITS

 Stan

3.72

Stan

2.59

stan

1.59

 Stanley

1.38

 Carl

1.22

 Stanford

1.18

Sno

1.15

 Brad

1.09

 Wally

1.09

 Coul

1.05

Activations Density 0.016%

references to the name "Stan" followed by varying numbers

repeated mentions of the name "Stan."

No Comments

No Known Activations