INDEX

Explanations

words related to data analytics and statistical analysis

oai_token-act-pair · gpt-3.5-turbo

terminology related to algorithms and data processing

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

—

-0.64

 âĢķ

-0.55

 lousy

-0.55

—

-0.55

-0.52

 egreg

-0.52

––

-0.50

 Slaughter

-0.49

 Guant

-0.49

"—

-0.48

POSITIVE LOGITS

 accordingly

0.72

iour

0.72

 thereto

0.70

 learnt

0.68

sequently

0.66

urther

0.65

 realise

0.64

ibilities

0.62

 favourable

0.60

 consequ

0.60

Activations Density 1.282%

words related to data analytics and statistical analysis

terminology related to algorithms and data processing

No Comments

No Known Activations