INDEX

Explanations

references to specific locations or landmarks

oai_token-act-pair · gpt-3.5-turbo

specific names, places, or titles within a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 analyse

-1.08

 analys

-1.04

alys

-1.01

 analysed

-0.97

ensor

-0.91

EU

-0.89

 realise

-0.87

alysed

-0.85

 organis

-0.85

 behaviours

-0.83

POSITIVE LOGITS

 Appalachian

1.45

 Cherokee

1.35

 Prairie

1.34

 creek

1.34

 Twain

1.34

 Navajo

1.31

 Cedar

1.29

 Cemetery

1.27

 Railroad

1.25

 Appalach

1.24

Activations Density 0.515%

references to specific locations or landmarks

specific names, places, or titles within a text

No Comments

No Known Activations