INDEX

Explanations

terms related to simulations or modeling

oai_token-act-pair · gpt-3.5-turbo

references to computer simulations

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

nuts

-0.85

turn

-0.73

abouts

-0.72

nut

-0.72

reek

-0.70

çĦ

-0.69

umper

-0.69

stones

-0.68

holders

-0.65

uts

-0.65

POSITIVE LOGITS

 simulate

0.96

 simulations

0.93

 simulation

0.90

 simulated

0.87

 Simulation

0.84

ãĤ§

0.80

eer

0.79

eers

0.79

ulators

0.78

iliar

0.73

Activations Density 0.019%

terms related to simulations or modeling

references to computer simulations

No Comments

No Known Activations