INDEX

Explanations

programming code snippets containing syntax elements like function names and variable assignments

oai_token-act-pair · gpt-3.5-turbo

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

 Chattanooga

-0.75

 Head

-0.74

 Mercy

-0.69

Go

-0.69

 linger

-0.67

ped

-0.67

Elk

-0.67

 Thomas

-0.67

 Nest

-0.66

Luc

-0.66

POSITIVE LOGITS

1.84

(-

1.71

((

1.67

([

1.59

($

1.59

(_

1.59

(\

1.50

("

1.49

('

1.46

Activations Density 0.101%

programming code snippets containing syntax elements like function names and variable assignments

No Comments

No Known Activations