INDEX

Explanations

dates expressed in a specific format

oai_token-act-pair · gpt-3.5-turbo

sections of text that contain numerical data or references to statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ensor

-0.86

afety

-0.76

 Zoro

-0.68

pload

-0.66

phabet

-0.64

osterone

-0.63

 Codec

-0.63

 Onion

-0.61

}}}

-0.61

 Cipher

-0.61

POSITIVE LOGITS

0.90

0.88

0.87

0.85

0.84

0.83

0.81

early

0.79

Activations Density 0.037%

dates expressed in a specific format

sections of text that contain numerical data or references to statistical information

No Comments

No Known Activations