INDEX

Explanations

mentions of memory-related terms, such as "memory bandwidth" and "memory usage."

oai_token-act-pair · gpt-3.5-turbo

references to memory usage and management

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

jon

-0.85

kef

-0.82

Riy

-0.81

zag

-0.76

keye

-0.75

OPLE

-0.75

glers

-0.74

cliffe

-0.73

kok

-0.73

doms

-0.70

POSITIVE LOGITS

 consolidation

0.96

 storage

0.94

 allocation

0.87

 retrieval

0.84

 dumps

0.84

 bandwidth

0.84

 chips

0.80

Usage

0.77

Memory

0.76

 memory

0.76

Activations Density 0.026%

mentions of memory-related terms, such as "memory bandwidth" and "memory usage."

references to memory usage and management

No Comments

No Known Activations