INDEX

Explanations

commands or actions related to file manipulation and programming

oai_token-act-pair · gpt-3.5-turbo

technical terms related to data processing and manipulation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

fare

-0.79

stood

-0.77

occup

-0.71

soType

-0.70

uro

-0.69

scar

-0.69

wagon

-0.68

clerosis

-0.67

udence

-0.66

atics

-0.64

POSITIVE LOGITS

 batches

0.86

 incoming

0.83

 downloaded

0.82

 files

0.81

 arbitrary

0.80

 cached

0.79

 duplicate

0.77

 manually

0.77

 chunks

0.76

XML

0.76

Activations Density 0.261%

commands or actions related to file manipulation and programming

technical terms related to data processing and manipulation

No Comments

No Known Activations