INDEX

Explanations

keywords related to directories and file paths in a computer system

oai_token-act-pair · gpt-3.5-turbo

terms related to file system directories and organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

acted

-0.82

acting

-0.81

akening

-0.74

oria

-0.74

rained

-0.72

laws

-0.72

 damned

-0.71

 Wilde

-0.71

stakes

-0.70

terson

-0.70

POSITIVE LOGITS

 directories

1.00

 directory

0.94

 descriptor

0.84

 Directory

0.83

"/

0.79

directory

0.78

'/

0.77

 separ

0.75

 travers

0.75

~/.

0.74

Activations Density 0.017%

keywords related to directories and file paths in a computer system

terms related to file system directories and organization

No Comments

No Known Activations