INDEX

Explanations

complex strings of characters, possibly related to coding or technical terms

oai_token-act-pair · gpt-3.5-turbo

symbols that represent currency or financial terms

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

 Shutterstock

-0.77

 sacrific

-0.76

 Hear

-0.71

 closest

-0.71

Jem

-0.70

-0.69

 Sammy

-0.69

 Devi

-0.67

 Claud

-0.67

 nicely

-0.66

POSITIVE LOGITS

vernment

0.89

economic

0.87

cation

0.85

cre

0.85

ective

0.85

0.83

uthor

0.83

netic

0.82

mental

0.80

cult

0.80

Activations Density 0.274%

complex strings of characters, possibly related to coding or technical terms

symbols that represent currency or financial terms

No Comments

No Known Activations