INDEX

Explanations

key terms related to technology or data science, specifically focusing on technical tools and concepts

oai_token-act-pair · gpt-3.5-turbo

terms related to various types of artifacts or elements in a gaming or digital context

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

IB

-0.81

NF

-0.78

Eh

-0.77

AA

-0.75

Wi

-0.74

 acknow

-0.74

Um

-0.73

 estab

-0.73

 Unch

-0.73

Ic

-0.72

POSITIVE LOGITS

space

1.44

floor

1.44

drop

1.44

bill

1.44

bind

1.44

shop

1.43

drive

1.43

cover

1.43

stand

1.42

travel

1.42

Activations Density 0.326%

key terms related to technology or data science, specifically focusing on technical tools and concepts

terms related to various types of artifacts or elements in a gaming or digital context

No Comments

No Known Activations