INDEX

Explanations

keywords related to loading or reading data or variables

oai_token-act-pair · gpt-3.5-turbo

terms related to the action of loading 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 @ 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

esan

-0.83

pai

-0.83

Ĭ±

-0.81

apolis

-0.81

perty

-0.79

ces

-0.76

oeuv

-0.75

von

-0.73

Ĥİ

-0.73

eur

-0.73

POSITIVE LOGITS

strap

0.96

 load

0.93

 Load

0.91

loading

0.91

 loads

0.91

 loader

0.89

load

0.85

loader

0.80

ahead

0.80

loaded

0.78

Activations Density 0.013%

keywords related to loading or reading data or variables

terms related to the action of loading in various contexts

No Comments

No Known Activations