INDEX

Explanations

strategies or tactics mentioned within the text

oai_token-act-pair · gpt-3.5-turbo

references to various strategies being implemented or discussed

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

Negative Logits

brance

-0.79

ouple

-0.68

head

-0.67

 behold

-0.65

nder

-0.65

 ransom

-0.63

iam

-0.61

 dock

-0.61

 Flesh

-0.60

roma

-0.60

POSITIVE LOGITS

 strategies

3.19

 Strategies

2.15

 techniques

1.91

 tactics

1.77

 methods

1.75

 behaviors

1.66

 approaches

1.59

 solutions

1.58

 mechanisms

1.58

 theories

1.57

Activations Density 0.014%

strategies or tactics mentioned within the text

references to various strategies being implemented or discussed

No Known Activations