INDEX

Explanations

specific identifiers or codes in a structured format

oai_token-act-pair · gpt-3.5-turbo

key identifiers and references to specific events or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 realise

-0.85

 analyse

-0.77

 realised

-0.76

 util

-0.76

 organise

-0.75

 recognise

-0.75

 favourites

-0.73

 whilst

-0.70

 fulfil

-0.69

 onwards

-0.69

POSITIVE LOGITS

 Arpaio

0.78

HHS

0.74

DOE

0.74

 Anchorage

0.73

 Congressional

0.73

 POLITICO

0.72

 Amtrak

0.72

 DeVos

0.72

 Appalachian

0.71

 Albuquerque

0.71

Activations Density 2.454%

specific identifiers or codes in a structured format

key identifiers and references to specific events or situations

No Comments

No Known Activations