INDEX

Explanations

references to models, both in the context of fashion and other fields

oai_token-act-pair · gpt-3.5-turbo

mentions of the term "model" 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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

vernment

-1.06

ulhu

-0.86

usters

-0.79

kefeller

-0.78

lins

-0.77

olulu

-0.77

azar

-0.74

tein

-0.73

reath

-0.73

inness

-0.73

POSITIVE LOGITS

model

0.83

 Mayhem

0.79

)=(

0.70

models

0.70

 photographed

0.69

Upload

0.69

 Penal

0.67

aldehyde

0.66

 Blueprint

0.62

hetical

0.61

Activations Density 0.018%

references to models, both in the context of fashion and other fields

mentions of the term "model" in various contexts

No Comments

No Known Activations