INDEX

Explanations

numerical values indicating memory capacity

oai_token-act-pair · gpt-3.5-turbo

quantities and specifications related to memory and storage capacities

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

ashtra

-0.85

ĸļ

-0.79

andise

-0.77

ority

-0.76

ansen

-0.74

orical

-0.73

acus

-0.71

ItemTracker

-0.71

orie

-0.71

bara

-0.68

POSITIVE LOGITS

0.88

GB

0.83

 bytes

0.80

bit

0.79

Bit

0.79

Gb

0.76

PDATE

0.75

kHz

0.75

 integers

0.73

 currencies

0.72

Activations Density 0.070%

numerical values indicating memory capacity

quantities and specifications related to memory and storage capacities

No Comments

No Known Activations