INDEX

Explanations

technical terms related to networking devices or technology

oai_token-act-pair · gpt-3.5-turbo

occurrences of the abbreviation "AP" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĤ´ãĥ³

-0.70

terday

-0.69

ãĥĥãĥī

-0.69

 Luthor

-0.66

 Berm

-0.65

 Fenrir

-0.65

ãĤ¬

-0.64

 thumbs

-0.64

 Dracula

-0.64

 capitalist

-0.64

POSITIVE LOGITS

PLIED

1.09

PLE

1.06

PLIC

1.03

AP

1.00

PE

0.95

vantage

0.94

PAR

0.93

PL

0.90

PRO

0.89

sburg

0.88

Activations Density 0.009%

technical terms related to networking devices or technology

occurrences of the abbreviation "AP" in various contexts

No Comments

No Known Activations