INDEX

Explanations

data-related terms such as trends, growth rates, statistics, and survey findings

oai_token-act-pair · gpt-3.5-turbo

instances of trends and patterns in data or behavior

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

 Duchess

-0.65

ucl

-0.65

 Atomic

-0.64

 orbits

-0.62

 Prepar

-0.61

 warranties

-0.60

 preparations

-0.59

 Turing

-0.59

Rut

-0.59

missions

-0.58

POSITIVE LOGITS

 mirrored

1.28

 echoed

1.15

 replicated

1.12

 exacerbated

1.10

 persisted

1.09

 reflected

1.06

 manifested

1.04

 reversed

1.03

 compounded

1.03

 paralle

1.01

Activations Density 0.294%

data-related terms such as trends, growth rates, statistics, and survey findings

instances of trends and patterns in data or behavior

No Comments

No Known Activations