INDEX

Explanations

elements related to arrays or lists

oai_token-act-pair · gpt-3.5-turbo

references to "array" 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

 McKenna

-0.62

SF

-0.62

 Cthulhu

-0.61

OPLE

-0.60

mins

-0.60

missive

-0.59

doms

-0.58

SG

-0.58

Gordon

-0.58

orders

-0.58

POSITIVE LOGITS

 array

0.77

 subscript

0.76

itect

0.76

illary

0.74

arium

0.72

mble

0.72

naire

0.70

icter

0.70

Buffer

0.70

 sizes

0.68

Activations Density 0.019%

elements related to arrays or lists

references to "array" in various contexts

No Comments

No Known Activations