INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

entities associated with specific actions or individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ASA

-0.88

 paras

-0.79

ASP

-0.78

Sim

-0.78

Tib

-0.77

Sob

-0.75

 impedance

-0.75

ãĥ³ãĤ¸

-0.74

 acron

-0.74

 Symb

-0.72

POSITIVE LOGITS

ll

1.67

LL

1.35

ill

1.28

ell

1.28

ELL

1.21

oll

1.12

yll

1.12

ILL

1.12

rell

1.11

illy

1.10

Activations Density 0.219%

names of individuals

entities associated with specific actions or individuals

No Comments

No Known Activations