INDEX

Explanations

words related to physical locations or directions

oai_token-act-pair · gpt-3.5-turbo

variations of the suffix "add" and "ac"

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

 condol

-0.79

 Jinn

-0.74

 overdue

-0.65

 Reloaded

-0.61

 Reincarn

-0.60

 shine

-0.60

 Noon

-0.60

 sugg

-0.59

 coloring

-0.59

 Bills

-0.59

POSITIVE LOGITS

ngth

0.85

upon

0.82

 confines

0.76

opers

0.74

pling

0.74

ipes

0.72

udic

0.71

oslav

0.71

poll

0.71

ivari

0.70

Activations Density 0.084%

words related to physical locations or directions

variations of the suffix "add" and "ac"

No Comments

No Known Activations